panda/bettafish-company
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add BERTopic.

Browse Source
This commit is contained in:
戒酒的李白
2025-08-12 19:01:20 +08:00
parent e2323d579c
commit c5c530775e
256 changed files with 28666 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
LLMTopicDetection_BERTopic/docs/algorithm/1. embeddings.svg
+32
View File
@@ -0,0 +1,32 @@
<svg width="228" height="113" viewBox="0 0 228 113" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M68.7889 40.7606L54.4174 26.3594C54.1819 26.1238 53.8638 26 53.5317 26H16.34C14.4403 26 12.8962 27.5352 12.8962 29.4337L12.8765 92.5594C12.8765 94.4578 14.4219 96 16.3209 96H65.6905C67.5889 96 69.1343 94.459 69.1349 92.5613L69.1533 41.6413C69.1533 41.3098 69.0225 40.9949 68.7889 40.7606ZM66.634 92.5606C66.634 93.0806 66.2105 93.501 65.6905 93.501H16.3209C15.8003 93.501 15.3768 93.0844 15.3768 92.5644L15.3965 29.4362C15.3965 28.9162 15.8194 28.5003 16.34 28.5003H53.013L66.6517 42.1632L66.634 92.5606Z" fill="black"/>
<path d="M62.2626 40.3752H57.1876C55.8613 40.3752 54.7508 39.3098 54.7508 37.9835V27.2343C54.7508 26.5435 54.1908 25.9841 53.5006 25.9841C52.8105 25.9841 52.2505 26.5441 52.2505 27.2343V37.9835C52.2505 40.6889 54.4816 42.8749 57.187 42.8749H62.2619C62.9521 42.8749 63.5127 42.3162 63.5127 41.6254C63.5127 40.9346 62.9527 40.3752 62.2626 40.3752Z" fill="black"/>
<path d="M78.7584 30.7822L64.387 16.374C64.1514 16.1384 63.8333 16 63.5019 16H26.3095C24.4105 16 22.8746 17.5581 22.8746 19.4571V27.2343C22.8746 27.9251 23.434 28.4844 24.1248 28.4844C24.8156 28.4844 25.3749 27.9244 25.3749 27.2343V19.4571C25.3749 18.9371 25.7902 18.5003 26.3102 18.5003H62.9838L76.6232 32.1689L76.6041 82.574C76.6041 83.0933 76.1813 83.4997 75.6613 83.4997H67.8841C67.1933 83.4997 66.634 84.0597 66.634 84.7498C66.634 85.44 67.1933 86 67.8841 86H75.6613C77.5603 86 79.1044 84.4717 79.1038 82.5733L79.1235 31.6667C79.1235 31.3352 78.9914 31.0165 78.7584 30.7822Z" fill="black"/>
<path d="M72.2333 30.3746H67.1584C65.8321 30.3746 64.7508 29.339 64.7508 28.0127V17.2635C64.7508 16.5733 64.1908 16.0133 63.5006 16.0133C62.8105 16.0133 62.2505 16.5733 62.2505 17.2635V28.0127C62.2505 30.7181 64.453 32.8749 67.1578 32.8749H72.2327C72.9229 32.8749 73.4835 32.3156 73.4835 31.6248C73.4835 30.934 72.9235 30.3746 72.2333 30.3746Z" fill="black"/>
<path d="M22.7838 46.6248H19.7413C19.0511 46.6248 18.4911 47.1841 18.4911 47.8749C18.4911 48.5657 19.0511 49.1251 19.7413 49.1251H22.7838C23.4733 49.1251 24.034 48.5657 24.034 47.8749C24.034 47.1841 23.4733 46.6248 22.7838 46.6248Z" fill="black"/>
<path d="M62.2429 46.6248H28.3991C27.7076 46.6248 27.1489 47.1841 27.1489 47.8749C27.1489 48.5657 27.7083 49.1251 28.3991 49.1251H62.2429C62.9337 49.1251 63.493 48.5657 63.493 47.8749C63.493 47.1841 62.9337 46.6248 62.2429 46.6248Z" fill="black"/>
<path d="M62.2429 52.8749H52.7603C52.0695 52.8749 51.5102 53.4343 51.5102 54.1251C51.5102 54.8159 52.0695 55.3752 52.7603 55.3752H62.2429C62.9337 55.3752 63.493 54.8159 63.493 54.1251C63.493 53.4343 62.9337 52.8749 62.2429 52.8749Z" fill="black"/>
<path d="M47.1457 52.8749H19.7419C19.0518 52.8749 18.4918 53.4343 18.4918 54.1251C18.4918 54.8159 19.0518 55.3752 19.7419 55.3752H47.1457C47.8353 55.3752 48.3959 54.8159 48.3959 54.1251C48.3959 53.4343 47.8353 52.8749 47.1457 52.8749Z" fill="black"/>
<path d="M62.2429 59.1245H19.7419C19.0518 59.1245 18.4918 59.6845 18.4918 60.3746C18.4918 61.0648 19.0518 61.6248 19.7419 61.6248H62.2429C62.9337 61.6248 63.493 61.0648 63.493 60.3746C63.493 59.6845 62.9337 59.1245 62.2429 59.1245Z" fill="black"/>
<path d="M62.2429 77.8749H19.7419C19.0518 77.8749 18.4918 78.4349 18.4918 79.1251C18.4918 79.8152 19.0518 80.3752 19.7419 80.3752H62.2429C62.9337 80.3752 63.493 79.8152 63.493 79.1251C63.493 78.4349 62.9337 77.8749 62.2429 77.8749Z" fill="black"/>
<path d="M22.7838 65.3746H19.7413C19.0511 65.3746 18.4911 65.9346 18.4911 66.6248C18.4911 67.3149 19.0511 67.8749 19.7413 67.8749H22.7838C23.4733 67.8749 24.034 67.3149 24.034 66.6248C24.034 65.9346 23.4733 65.3746 22.7838 65.3746Z" fill="black"/>
<path d="M62.2429 65.3746H28.3991C27.7076 65.3746 27.1489 65.9346 27.1489 66.6248C27.1489 67.3149 27.7083 67.8749 28.3991 67.8749H62.2429C62.9337 67.8749 63.493 67.3149 63.493 66.6248C63.493 65.9346 62.9337 65.3746 62.2429 65.3746Z" fill="black"/>
<path d="M62.2429 71.6248H52.7603C52.0695 71.6248 51.5102 72.1848 51.5102 72.8749C51.5102 73.5651 52.0695 74.1251 52.7603 74.1251H62.2429C62.9337 74.1251 63.493 73.5651 63.493 72.8749C63.493 72.1848 62.9337 71.6248 62.2429 71.6248Z" fill="black"/>
<path d="M47.1457 71.6248H19.7419C19.0518 71.6248 18.4918 72.1848 18.4918 72.8749C18.4918 73.5651 19.0518 74.1251 19.7419 74.1251H47.1457C47.8353 74.1251 48.3959 73.5651 48.3959 72.8749C48.3959 72.1848 47.8353 71.6248 47.1457 71.6248Z" fill="black"/>
<path d="M22.7838 84.1245H19.7413C19.0511 84.1245 18.4911 84.6845 18.4911 85.3746C18.4911 86.0648 19.0511 86.6248 19.7413 86.6248H22.7838C23.4733 86.6248 24.034 86.0648 24.034 85.3746C24.034 84.6845 23.4733 84.1245 22.7838 84.1245Z" fill="black"/>
<path d="M62.2429 84.1245H28.3991C27.7076 84.1245 27.1489 84.6845 27.1489 85.3746C27.1489 86.0648 27.7083 86.6248 28.3991 86.6248H62.2429C62.9337 86.6248 63.493 86.0648 63.493 85.3746C63.493 84.6845 62.9337 84.1245 62.2429 84.1245Z" fill="black"/>
<path d="M72.2143 36.6248H64.7952C64.1044 36.6248 63.5451 37.1841 63.5451 37.8749C63.5451 38.5657 64.1044 39.1251 64.7952 39.1251H72.2136C72.9044 39.1251 73.4644 38.5657 73.4644 37.8749C73.4644 37.1841 72.9051 36.6248 72.2143 36.6248Z" fill="black"/>
<path d="M72.2137 42.8749H67.8841C67.1933 42.8749 66.634 43.4343 66.634 44.1251C66.634 44.8159 67.1933 45.3752 67.8841 45.3752H72.2137C72.9044 45.3752 73.4638 44.8159 73.4638 44.1251C73.4638 43.4343 72.9044 42.8749 72.2137 42.8749Z" fill="black"/>
<path d="M72.2137 49.1245H67.8841C67.1933 49.1245 66.634 49.6838 66.634 50.3746C66.634 51.0654 67.1933 51.6248 67.8841 51.6248H72.2137C72.9044 51.6248 73.4638 51.0654 73.4638 50.3746C73.4638 49.6838 72.9044 49.1245 72.2137 49.1245Z" fill="black"/>
<path d="M72.2136 67.8749H68.267C67.5775 67.8749 67.0168 68.4349 67.0168 69.1251C67.0168 69.8152 67.5775 70.3752 68.267 70.3752H72.2136C72.9044 70.3752 73.4638 69.8152 73.4638 69.1251C73.4638 68.4349 72.9044 67.8749 72.2136 67.8749Z" fill="black"/>
<path d="M72.2137 55.3746H67.8841C67.1933 55.3746 66.634 55.9346 66.634 56.6248C66.634 57.3149 67.1933 57.8749 67.8841 57.8749H72.2137C72.9044 57.8749 73.4638 57.3149 73.4638 56.6248C73.4638 55.934 72.9044 55.3746 72.2137 55.3746Z" fill="black"/>
<path d="M72.2137 61.6248H67.8841C67.1933 61.6248 66.634 62.1848 66.634 62.8749C66.634 63.5651 67.1933 64.1251 67.8841 64.1251H72.2137C72.9044 64.1251 73.4638 63.5651 73.4638 62.8749C73.4638 62.1848 72.9044 61.6248 72.2137 61.6248Z" fill="black"/>
<path d="M72.2137 74.1244H67.8841C67.1933 74.1244 66.634 74.6844 66.634 75.3746C66.634 76.0648 67.1933 76.6248 67.8841 76.6248H72.2137C72.9044 76.6248 73.4638 76.0648 73.4638 75.3746C73.4638 74.6844 72.9044 74.1244 72.2137 74.1244Z" fill="black"/>
<path d="M155.061 57.0607C155.646 56.4749 155.646 55.5251 155.061 54.9393L145.515 45.3934C144.929 44.8076 143.979 44.8076 143.393 45.3934C142.808 45.9792 142.808 46.9289 143.393 47.5147L151.879 56L143.393 64.4853C142.808 65.0711 142.808 66.0208 143.393 66.6066C143.979 67.1924 144.929 67.1924 145.515 66.6066L155.061 57.0607ZM98 57.5H154V54.5H98V57.5Z" fill="black"/>
<path d="M189 13H180V103H189" stroke="black" stroke-width="2"/>
<path d="M204 13H213V103H204" stroke="black" stroke-width="2"/>
<path d="M194.746 16.6543L196 19.2148L198.062 16.666H198.918L196.322 19.8066L197.98 23H197.219L195.883 20.3281L193.721 23H192.871L195.572 19.7305L193.984 16.6543H194.746ZM194.746 30.6543L196 33.2148L198.062 30.666H198.918L196.322 33.8066L197.98 37H197.219L195.883 34.3281L193.721 37H192.871L195.572 33.7305L193.984 30.6543H194.746ZM194.898 50.5723C194.902 50.4395 194.953 50.3242 195.051 50.2266C195.148 50.1289 195.266 50.0781 195.402 50.0742C195.543 50.0742 195.658 50.1211 195.748 50.2148C195.838 50.3086 195.879 50.4258 195.871 50.5664C195.863 50.7031 195.811 50.8184 195.713 50.9121C195.615 51.0059 195.498 51.0527 195.361 51.0527C195.221 51.0566 195.105 51.0137 195.016 50.9238C194.926 50.8301 194.887 50.7129 194.898 50.5723ZM194.898 64.5723C194.902 64.4395 194.953 64.3242 195.051 64.2266C195.148 64.1289 195.266 64.0781 195.402 64.0742C195.543 64.0742 195.658 64.1211 195.748 64.2148C195.838 64.3086 195.879 64.4258 195.871 64.5664C195.863 64.7031 195.811 64.8184 195.713 64.9121C195.615 65.0059 195.498 65.0527 195.361 65.0527C195.221 65.0566 195.105 65.0137 195.016 64.9238C194.926 64.8301 194.887 64.7129 194.898 64.5723ZM194.898 78.5723C194.902 78.4395 194.953 78.3242 195.051 78.2266C195.148 78.1289 195.266 78.0781 195.402 78.0742C195.543 78.0742 195.658 78.1211 195.748 78.2148C195.838 78.3086 195.879 78.4258 195.871 78.5664C195.863 78.7031 195.811 78.8184 195.713 78.9121C195.615 79.0059 195.498 79.0527 195.361 79.0527C195.221 79.0566 195.105 79.0137 195.016 78.9238C194.926 78.8301 194.887 78.7129 194.898 78.5723ZM194.746 86.6543L196 89.2148L198.062 86.666H198.918L196.322 89.8066L197.98 93H197.219L195.883 90.3281L193.721 93H192.871L195.572 89.7305L193.984 86.6543H194.746Z" fill="black"/>
<path d="M203.047 19.2891L202.074 25H201.617L202.504 19.8945L200.906 20.457L200.984 20.0039L202.961 19.2891H203.047Z" fill="black"/>
<path d="M203.523 38.5977L203.461 39H200.004L200.059 38.6211L202.176 36.5234C202.332 36.3672 202.496 36.1992 202.668 36.0195C202.842 35.8398 202.995 35.6471 203.125 35.4414C203.258 35.2357 203.342 35.0169 203.379 34.7852C203.41 34.5638 203.392 34.3672 203.324 34.1953C203.259 34.0234 203.15 33.888 202.996 33.7891C202.842 33.6875 202.651 33.6354 202.422 33.6328C202.161 33.6302 201.93 33.6875 201.727 33.8047C201.526 33.9219 201.361 34.0807 201.23 34.2812C201.103 34.4818 201.018 34.7044 200.977 34.9492H200.523C200.568 34.6237 200.677 34.3307 200.852 34.0703C201.026 33.8099 201.249 33.6055 201.52 33.457C201.793 33.306 202.098 33.2318 202.434 33.2344C202.736 33.237 202.999 33.2995 203.223 33.4219C203.449 33.5443 203.618 33.7188 203.73 33.9453C203.842 34.1719 203.88 34.4388 203.844 34.7461C203.82 34.9518 203.762 35.1497 203.668 35.3398C203.574 35.5273 203.46 35.7083 203.324 35.8828C203.191 36.0547 203.049 36.2188 202.898 36.375C202.747 36.5286 202.602 36.6745 202.461 36.8125L200.645 38.5977H203.523Z" fill="black"/>
<path d="M201.082 94.6953L200.512 98H200.055L200.785 93.7734H201.223L201.082 94.6953ZM200.828 95.625L200.645 95.5078C200.697 95.2786 200.776 95.056 200.883 94.8398C200.99 94.6211 201.122 94.4258 201.281 94.2539C201.443 94.0794 201.628 93.9427 201.836 93.8438C202.047 93.7422 202.281 93.6927 202.539 93.6953C202.771 93.6979 202.962 93.7409 203.113 93.8242C203.267 93.9049 203.385 94.0182 203.469 94.1641C203.552 94.3073 203.604 94.4727 203.625 94.6602C203.648 94.8451 203.646 95.0417 203.617 95.25L203.152 98H202.691L203.164 95.2422C203.193 95.0391 203.191 94.8516 203.16 94.6797C203.132 94.5052 203.059 94.3659 202.941 94.2617C202.824 94.1549 202.648 94.1016 202.414 94.1016C202.206 94.099 202.014 94.1419 201.84 94.2305C201.665 94.3164 201.509 94.4336 201.371 94.582C201.236 94.7279 201.121 94.8919 201.027 95.0742C200.936 95.2539 200.87 95.4375 200.828 95.625Z" fill="black"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 11 KiB

LLMTopicDetection_BERTopic/docs/algorithm/2. reduction.svg
+17
View File
@@ -0,0 +1,17 @@
<svg width="228" height="113" viewBox="0 0 228 113" fill="none" xmlns="http://www.w3.org/2000/svg">
<path d="M51 13H42V103H51" stroke="black" stroke-width="2"/>
<path d="M66 13H75V103H66" stroke="black" stroke-width="2"/>
<path d="M56.7461 16.6543L58 19.2148L60.0625 16.666H60.918L58.3223 19.8066L59.9805 23H59.2188L57.8828 20.3281L55.7207 23H54.8711L57.5723 19.7305L55.9844 16.6543H56.7461ZM56.7461 30.6543L58 33.2148L60.0625 30.666H60.918L58.3223 33.8066L59.9805 37H59.2188L57.8828 34.3281L55.7207 37H54.8711L57.5723 33.7305L55.9844 30.6543H56.7461ZM56.8984 50.5723C56.9023 50.4395 56.9531 50.3242 57.0508 50.2266C57.1484 50.1289 57.2656 50.0781 57.4023 50.0742C57.543 50.0742 57.6582 50.1211 57.748 50.2148C57.8379 50.3086 57.8789 50.4258 57.8711 50.5664C57.8633 50.7031 57.8105 50.8184 57.7129 50.9121C57.6152 51.0059 57.498 51.0527 57.3613 51.0527C57.2207 51.0566 57.1055 51.0137 57.0156 50.9238C56.9258 50.8301 56.8867 50.7129 56.8984 50.5723ZM56.8984 64.5723C56.9023 64.4395 56.9531 64.3242 57.0508 64.2266C57.1484 64.1289 57.2656 64.0781 57.4023 64.0742C57.543 64.0742 57.6582 64.1211 57.748 64.2148C57.8379 64.3086 57.8789 64.4258 57.8711 64.5664C57.8633 64.7031 57.8105 64.8184 57.7129 64.9121C57.6152 65.0059 57.498 65.0527 57.3613 65.0527C57.2207 65.0566 57.1055 65.0137 57.0156 64.9238C56.9258 64.8301 56.8867 64.7129 56.8984 64.5723ZM56.8984 78.5723C56.9023 78.4395 56.9531 78.3242 57.0508 78.2266C57.1484 78.1289 57.2656 78.0781 57.4023 78.0742C57.543 78.0742 57.6582 78.1211 57.748 78.2148C57.8379 78.3086 57.8789 78.4258 57.8711 78.5664C57.8633 78.7031 57.8105 78.8184 57.7129 78.9121C57.6152 79.0059 57.498 79.0527 57.3613 79.0527C57.2207 79.0566 57.1055 79.0137 57.0156 78.9238C56.9258 78.8301 56.8867 78.7129 56.8984 78.5723ZM56.7461 86.6543L58 89.2148L60.0625 86.666H60.918L58.3223 89.8066L59.9805 93H59.2188L57.8828 90.3281L55.7207 93H54.8711L57.5723 89.7305L55.9844 86.6543H56.7461Z" fill="black"/>
<path d="M65.0469 19.2891L64.0742 25H63.6172L64.5039 19.8945L62.9062 20.457L62.9844 20.0039L64.9609 19.2891H65.0469Z" fill="black"/>
<path d="M65.5234 38.5977L65.4609 39H62.0039L62.0586 38.6211L64.1758 36.5234C64.332 36.3672 64.4961 36.1992 64.668 36.0195C64.8424 35.8398 64.9948 35.6471 65.125 35.4414C65.2578 35.2357 65.3424 35.0169 65.3789 34.7852C65.4102 34.5638 65.3919 34.3672 65.3242 34.1953C65.2591 34.0234 65.1497 33.888 64.9961 33.7891C64.8424 33.6875 64.651 33.6354 64.4219 33.6328C64.1615 33.6302 63.9297 33.6875 63.7266 33.8047C63.526 33.9219 63.3607 34.0807 63.2305 34.2812C63.1029 34.4818 63.0182 34.7044 62.9766 34.9492H62.5234C62.5677 34.6237 62.6771 34.3307 62.8516 34.0703C63.026 33.8099 63.2487 33.6055 63.5195 33.457C63.793 33.306 64.0977 33.2318 64.4336 33.2344C64.7357 33.237 64.9987 33.2995 65.2227 33.4219C65.4492 33.5443 65.6185 33.7188 65.7305 33.9453C65.8424 34.1719 65.8802 34.4388 65.8438 34.7461C65.8203 34.9518 65.7617 35.1497 65.668 35.3398C65.5742 35.5273 65.4596 35.7083 65.3242 35.8828C65.1914 36.0547 65.0495 36.2188 64.8984 36.375C64.7474 36.5286 64.6016 36.6745 64.4609 36.8125L62.6445 38.5977H65.5234Z" fill="black"/>
<path d="M63.082 94.6953L62.5117 98H62.0547L62.7852 93.7734H63.2227L63.082 94.6953ZM62.8281 95.625L62.6445 95.5078C62.6966 95.2786 62.776 95.056 62.8828 94.8398C62.9896 94.6211 63.1224 94.4258 63.2812 94.2539C63.4427 94.0794 63.6276 93.9427 63.8359 93.8438C64.0469 93.7422 64.2812 93.6927 64.5391 93.6953C64.7708 93.6979 64.9622 93.7409 65.1133 93.8242C65.2669 93.9049 65.3854 94.0182 65.4688 94.1641C65.5521 94.3073 65.6042 94.4727 65.625 94.6602C65.6484 94.8451 65.6458 95.0417 65.6172 95.25L65.1523 98H64.6914L65.1641 95.2422C65.1927 95.0391 65.1914 94.8516 65.1602 94.6797C65.1315 94.5052 65.0586 94.3659 64.9414 94.2617C64.8242 94.1549 64.6484 94.1016 64.4141 94.1016C64.2057 94.099 64.0143 94.1419 63.8398 94.2305C63.6654 94.3164 63.5091 94.4336 63.3711 94.582C63.2357 94.7279 63.1211 94.8919 63.0273 95.0742C62.9362 95.2539 62.8698 95.4375 62.8281 95.625Z" fill="black"/>
<path d="M161 13H152V103H161" stroke="black" stroke-width="2"/>
<path d="M176 13H185V103H176" stroke="black" stroke-width="2"/>
<path d="M166.746 24.6543L168 27.2148L170.062 24.666H170.918L168.322 27.8066L169.98 31H169.219L167.883 28.3281L165.721 31H164.871L167.572 27.7305L165.984 24.6543H166.746ZM166.746 38.6543L168 41.2148L170.062 38.666H170.918L168.322 41.8066L169.98 45H169.219L167.883 42.3281L165.721 45H164.871L167.572 41.7305L165.984 38.6543H166.746ZM166.746 52.6543L168 55.2148L170.062 52.666H170.918L168.322 55.8066L169.98 59H169.219L167.883 56.3281L165.721 59H164.871L167.572 55.7305L165.984 52.6543H166.746ZM166.746 66.6543L168 69.2148L170.062 66.666H170.918L168.322 69.8066L169.98 73H169.219L167.883 70.3281L165.721 73H164.871L167.572 69.7305L165.984 66.6543H166.746ZM166.746 80.6543L168 83.2148L170.062 80.666H170.918L168.322 83.8066L169.98 87H169.219L167.883 84.3281L165.721 87H164.871L167.572 83.7305L165.984 80.6543H166.746Z" fill="black"/>
<path d="M173.785 28.7168L173.056 33H172.713L173.378 29.1709L172.18 29.5928L172.238 29.2529L173.721 28.7168H173.785Z" fill="black"/>
<path d="M174.143 46.6982L174.096 47H171.503L171.544 46.7158L173.132 45.1426C173.249 45.0254 173.372 44.8994 173.501 44.7646C173.632 44.6299 173.746 44.4854 173.844 44.3311C173.943 44.1768 174.007 44.0127 174.034 43.8389C174.058 43.6729 174.044 43.5254 173.993 43.3965C173.944 43.2676 173.862 43.166 173.747 43.0918C173.632 43.0156 173.488 42.9766 173.316 42.9746C173.121 42.9727 172.947 43.0156 172.795 43.1035C172.645 43.1914 172.521 43.3105 172.423 43.4609C172.327 43.6113 172.264 43.7783 172.232 43.9619H171.893C171.926 43.7178 172.008 43.498 172.139 43.3027C172.27 43.1074 172.437 42.9541 172.64 42.8428C172.845 42.7295 173.073 42.6738 173.325 42.6758C173.552 42.6777 173.749 42.7246 173.917 42.8164C174.087 42.9082 174.214 43.0391 174.298 43.209C174.382 43.3789 174.41 43.5791 174.383 43.8096C174.365 43.9639 174.321 44.1123 174.251 44.2549C174.181 44.3955 174.095 44.5312 173.993 44.6621C173.894 44.791 173.787 44.9141 173.674 45.0312C173.561 45.1465 173.451 45.2559 173.346 45.3594L171.983 46.6982H174.143Z" fill="black"/>
<path d="M172.622 58.6738L172.953 58.6768C173.127 58.6729 173.293 58.6396 173.451 58.5771C173.611 58.5146 173.746 58.4219 173.855 58.2988C173.967 58.1758 174.035 58.0215 174.061 57.8359C174.086 57.666 174.073 57.5176 174.022 57.3906C173.972 57.2617 173.889 57.1611 173.773 57.0889C173.658 57.0146 173.514 56.9766 173.34 56.9746C173.16 56.9727 172.997 57.0088 172.851 57.083C172.704 57.1572 172.582 57.2607 172.484 57.3936C172.389 57.5244 172.324 57.6768 172.291 57.8506H171.951C171.984 57.6182 172.066 57.4131 172.197 57.2354C172.33 57.0576 172.497 56.9199 172.698 56.8223C172.899 56.7227 173.117 56.6738 173.352 56.6758C173.582 56.6758 173.781 56.7256 173.949 56.8252C174.117 56.9229 174.242 57.0596 174.324 57.2354C174.406 57.4111 174.434 57.6152 174.406 57.8477C174.387 58.0215 174.332 58.1748 174.242 58.3076C174.154 58.4385 174.043 58.5488 173.908 58.6387C173.775 58.7266 173.63 58.7939 173.472 58.8408C173.313 58.8857 173.154 58.9092 172.994 58.9111L172.587 58.9082L172.622 58.6738ZM172.575 58.9756L172.61 58.7441H172.977C173.146 58.748 173.307 58.7715 173.457 58.8145C173.609 58.8574 173.742 58.9229 173.855 59.0107C173.971 59.0967 174.057 59.208 174.113 59.3447C174.172 59.4795 174.19 59.6416 174.169 59.8311C174.147 60.0186 174.096 60.1885 174.014 60.3408C173.934 60.4912 173.829 60.6201 173.7 60.7275C173.571 60.835 173.425 60.918 173.261 60.9766C173.097 61.0332 172.922 61.0605 172.736 61.0586C172.557 61.0566 172.393 61.0264 172.244 60.9678C172.096 60.9092 171.968 60.8271 171.86 60.7217C171.755 60.6143 171.676 60.4863 171.623 60.3379C171.572 60.1875 171.555 60.0215 171.57 59.8398L171.91 59.8428C171.893 60.0225 171.916 60.1807 171.98 60.3174C172.047 60.4541 172.146 60.5615 172.276 60.6396C172.409 60.7158 172.565 60.7549 172.745 60.7568C172.937 60.7588 173.108 60.7227 173.261 60.6484C173.415 60.5742 173.541 60.4688 173.639 60.332C173.738 60.1934 173.801 60.0293 173.826 59.8398C173.854 59.6406 173.83 59.4785 173.756 59.3535C173.682 59.2266 173.572 59.1328 173.428 59.0723C173.285 59.0117 173.123 58.9805 172.941 58.9785L172.575 58.9756Z" fill="black"/>
<path d="M174.444 73.623L174.397 73.9219H171.459L171.497 73.7051L173.914 70.7373H174.222L173.686 71.4727L171.945 73.623H174.444ZM174.298 70.7344L173.562 75H173.22L173.958 70.7344H174.298Z" fill="black"/>
<path d="M172.35 86.8877L172.074 86.8057L172.599 84.7344H174.67L174.623 85.0625H172.848L172.458 86.501C172.575 86.4229 172.703 86.3643 172.842 86.3252C172.98 86.2842 173.12 86.2646 173.261 86.2666C173.454 86.2666 173.621 86.3047 173.762 86.3809C173.902 86.4551 174.016 86.5566 174.102 86.6855C174.189 86.8125 174.249 86.958 174.28 87.1221C174.313 87.2842 174.32 87.4541 174.301 87.6318C174.277 87.8271 174.229 88.0117 174.157 88.1855C174.085 88.3594 173.988 88.5127 173.867 88.6455C173.746 88.7764 173.602 88.8789 173.434 88.9531C173.268 89.0273 173.079 89.0625 172.868 89.0586C172.69 89.0586 172.532 89.0293 172.394 88.9707C172.257 88.9121 172.142 88.8301 172.048 88.7246C171.954 88.6172 171.883 88.4922 171.834 88.3496C171.785 88.2051 171.761 88.0479 171.761 87.8779H172.089C172.089 88.0479 172.117 88.1992 172.174 88.332C172.23 88.4629 172.316 88.5664 172.432 88.6426C172.549 88.7188 172.698 88.7578 172.88 88.7598C173.044 88.7598 173.188 88.7295 173.311 88.6689C173.436 88.6084 173.542 88.5254 173.63 88.4199C173.72 88.3145 173.791 88.1943 173.844 88.0596C173.896 87.9248 173.934 87.7832 173.955 87.6348C173.973 87.5 173.971 87.3711 173.949 87.248C173.928 87.123 173.886 87.0117 173.823 86.9141C173.761 86.8145 173.677 86.7363 173.571 86.6797C173.466 86.6211 173.339 86.5898 173.19 86.5859C173.028 86.584 172.879 86.6094 172.742 86.6621C172.607 86.7148 172.477 86.79 172.35 86.8877Z" fill="black"/>
<path d="M134.061 62.0607C134.646 61.4749 134.646 60.5251 134.061 59.9393L124.515 50.3934C123.929 49.8076 122.979 49.8076 122.393 50.3934C121.808 50.9792 121.808 51.9289 122.393 52.5147L130.879 61L122.393 69.4853C121.808 70.0711 121.808 71.0208 122.393 71.6066C122.979 72.1924 123.929 72.1924 124.515 71.6066L134.061 62.0607ZM91 62.5H133V59.5H91V62.5Z" fill="black"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 9.9 KiB

LLMTopicDetection_BERTopic/docs/algorithm/3. cluster.svg
+14
View File
@@ -0,0 +1,14 @@
<svg width="228" height="113" viewBox="0 0 228 113" fill="none" xmlns="http://www.w3.org/2000/svg">
<rect x="32" y="12" width="12" height="12" fill="black"/>
<rect x="72" y="9" width="12" height="12" fill="black"/>
<rect x="60" y="32" width="12" height="12" fill="black"/>
<rect x="32" y="44" width="12" height="12" fill="black"/>
<circle cx="166" cy="53" r="6" fill="black"/>
<circle cx="180" cy="19" r="6" fill="black"/>
<circle cx="194" cy="44" r="6" fill="black"/>
<circle cx="154" cy="32" r="6" fill="black"/>
<path d="M90 98L95.1962 107H84.8038L90 98Z" fill="black"/>
<path d="M104 80L109.196 89H98.8038L104 80Z" fill="black"/>
<path d="M121 98L126.196 107H115.804L121 98Z" fill="black"/>
<path d="M127 74L132.196 83H121.804L127 74Z" fill="black"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 762 B

LLMTopicDetection_BERTopic/docs/algorithm/4. bow.svg
+29
View File
File diff suppressed because one or more lines are too long
Side by Side

After

Width:  |  Height:  |  Size: 42 KiB

LLMTopicDetection_BERTopic/docs/algorithm/5. ctfidf.svg
+23
View File
@@ -0,0 +1,23 @@
<svg width="228" height="113" viewBox="0 0 228 113" fill="none" xmlns="http://www.w3.org/2000/svg">
<line x1="59.8941" y1="40.3059" x2="59.8941" y2="62.85" stroke="black"/>
<line x1="57.9618" y1="40.3059" x2="57.9618" y2="62.85" stroke="black"/>
<line x1="99.1853" y1="40.6618" x2="99.1853" y2="63.2059" stroke="black"/>
<line x1="97.2529" y1="40.6618" x2="97.2529" y2="63.2059" stroke="black"/>
<path d="M51.3695 48.5401V49.794H41.5961V48.5401H51.3695ZM51.3695 53.3565V54.6104H41.5961V53.3565H51.3695Z" fill="#ABA9A9"/>
<path d="M107.229 46.0497L110.651 51.1708L114.084 46.0497H115.748L111.448 52.2606L115.924 58.7294H114.284L110.662 53.3739L107.053 58.7294H105.412L109.889 52.2606L105.588 46.0497H107.229Z" fill="#ABA9A9"/>
<path d="M187.412 51.0458V52.37H175.717V51.0458H187.412ZM182.221 45.5966V58.0184H180.815V45.5966H182.221Z" fill="#ABA9A9"/>
<path d="M126.172 42.3736V60.3736H122.785V42.3736H126.172ZM128.422 54.1627V53.9166C128.422 52.9869 128.555 52.1314 128.82 51.3502C129.086 50.5611 129.473 49.8775 129.981 49.2994C130.488 48.7213 131.113 48.272 131.856 47.9517C132.598 47.6236 133.449 47.4595 134.41 47.4595C135.371 47.4595 136.227 47.6236 136.977 47.9517C137.727 48.272 138.356 48.7213 138.863 49.2994C139.379 49.8775 139.77 50.5611 140.035 51.3502C140.301 52.1314 140.434 52.9869 140.434 53.9166V54.1627C140.434 55.0845 140.301 55.94 140.035 56.7291C139.77 57.5103 139.379 58.1939 138.863 58.7798C138.356 59.358 137.731 59.8072 136.988 60.1275C136.246 60.4478 135.395 60.608 134.434 60.608C133.473 60.608 132.617 60.4478 131.867 60.1275C131.125 59.8072 130.496 59.358 129.981 58.7798C129.473 58.1939 129.086 57.5103 128.82 56.7291C128.555 55.94 128.422 55.0845 128.422 54.1627ZM131.797 53.9166V54.1627C131.797 54.6939 131.844 55.19 131.938 55.6509C132.031 56.1119 132.18 56.5181 132.383 56.8697C132.594 57.2134 132.867 57.483 133.203 57.6783C133.539 57.8736 133.949 57.9713 134.434 57.9713C134.903 57.9713 135.305 57.8736 135.641 57.6783C135.977 57.483 136.246 57.2134 136.449 56.8697C136.653 56.5181 136.801 56.1119 136.895 55.6509C136.996 55.19 137.047 54.6939 137.047 54.1627V53.9166C137.047 53.4009 136.996 52.9166 136.895 52.4634C136.801 52.0025 136.649 51.5963 136.438 51.2447C136.235 50.8853 135.965 50.6041 135.629 50.4009C135.293 50.1978 134.887 50.0963 134.41 50.0963C133.934 50.0963 133.528 50.1978 133.192 50.4009C132.863 50.6041 132.594 50.8853 132.383 51.2447C132.18 51.5963 132.031 52.0025 131.938 52.4634C131.844 52.9166 131.797 53.4009 131.797 53.9166ZM150.535 47.6939H153.594V59.9517C153.594 61.108 153.336 62.0884 152.82 62.8931C152.313 63.7056 151.602 64.3189 150.688 64.733C149.774 65.1548 148.711 65.3658 147.5 65.3658C146.969 65.3658 146.406 65.2955 145.813 65.1548C145.227 65.0142 144.664 64.7955 144.125 64.4986C143.594 64.2017 143.149 63.8267 142.789 63.3736L144.278 61.3814C144.668 61.8345 145.121 62.1861 145.637 62.4361C146.153 62.6939 146.723 62.8228 147.348 62.8228C147.957 62.8228 148.473 62.7095 148.895 62.483C149.317 62.2642 149.641 61.94 149.867 61.5103C150.094 61.0884 150.207 60.5767 150.207 59.9752V50.6236L150.535 47.6939ZM142.004 54.1861V53.94C142.004 52.9713 142.121 52.0923 142.356 51.3033C142.598 50.5064 142.938 49.8228 143.375 49.2525C143.82 48.6822 144.36 48.2408 144.992 47.9283C145.625 47.6158 146.34 47.4595 147.137 47.4595C147.981 47.4595 148.688 47.6158 149.258 47.9283C149.828 48.2408 150.297 48.6861 150.664 49.2642C151.031 49.8345 151.317 50.5103 151.52 51.2916C151.731 52.065 151.895 52.9127 152.012 53.8345V54.3736C151.895 55.2564 151.719 56.0767 151.485 56.8345C151.25 57.5923 150.942 58.2564 150.559 58.8267C150.176 59.3892 149.699 59.8267 149.129 60.1392C148.567 60.4517 147.895 60.608 147.113 60.608C146.332 60.608 145.625 60.4478 144.992 60.1275C144.367 59.8072 143.832 59.358 143.387 58.7798C142.942 58.2017 142.598 57.522 142.356 56.7408C142.121 55.9595 142.004 55.108 142.004 54.1861ZM145.379 53.94V54.1861C145.379 54.7095 145.43 55.1978 145.531 55.6509C145.633 56.1041 145.789 56.5064 146 56.858C146.219 57.2017 146.488 57.4713 146.809 57.6666C147.137 57.8541 147.524 57.9478 147.969 57.9478C148.586 57.9478 149.09 57.8189 149.481 57.5611C149.871 57.2955 150.164 56.9322 150.36 56.4713C150.555 56.0103 150.668 55.4791 150.699 54.8775V53.3423C150.684 52.8502 150.617 52.4088 150.5 52.0181C150.383 51.6197 150.219 51.2798 150.008 50.9986C149.797 50.7173 149.524 50.4986 149.188 50.3423C148.852 50.1861 148.453 50.108 147.992 50.108C147.547 50.108 147.16 50.2095 146.832 50.4127C146.512 50.608 146.242 50.8775 146.024 51.2213C145.813 51.565 145.653 51.9713 145.543 52.44C145.434 52.9009 145.379 53.4009 145.379 53.94Z" fill="black"/>
<path d="M157.212 52.8801V52.6603C157.212 50.756 157.413 48.9738 157.813 47.3137C158.213 45.6535 158.736 44.1594 159.38 42.8312C160.035 41.5031 160.748 40.3752 161.519 39.4474C162.3 38.5099 163.067 37.8166 163.819 37.3674L164.244 38.5685C163.599 39.0275 162.96 39.6916 162.325 40.5607C161.7 41.4299 161.133 42.4748 160.626 43.6955C160.118 44.9162 159.712 46.2785 159.41 47.7824C159.107 49.2863 158.956 50.8976 158.956 52.6164V52.9094C158.956 54.6281 159.107 56.2394 159.41 57.7433C159.712 59.2473 160.118 60.6096 160.626 61.8303C161.133 63.0607 161.7 64.1154 162.325 64.9943C162.96 65.883 163.599 66.5666 164.244 67.0451L163.819 68.173C163.067 67.7238 162.3 67.0402 161.519 66.1223C160.748 65.2141 160.035 64.1008 159.38 62.7824C158.736 61.4738 158.213 59.9846 157.813 58.3146C157.413 56.6447 157.212 54.8332 157.212 52.8801Z" fill="#ABA9A9"/>
<path d="M221.935 53.2359V53.0162C221.935 51.1119 221.734 49.3297 221.334 47.6695C220.934 46.0093 220.411 44.5152 219.767 43.1871C219.112 41.8589 218.399 40.731 217.628 39.8033C216.847 38.8658 216.08 38.1724 215.328 37.7232L214.903 38.9244C215.548 39.3834 216.188 40.0474 216.822 40.9166C217.447 41.7857 218.014 42.8306 218.521 44.0513C219.029 45.272 219.435 46.6343 219.737 48.1382C220.04 49.6422 220.191 51.2535 220.191 52.9722V53.2652C220.191 54.9839 220.04 56.5953 219.737 58.0992C219.435 59.6031 219.029 60.9654 218.521 62.1861C218.014 63.4166 217.447 64.4713 216.822 65.3502C216.188 66.2388 215.548 66.9224 214.903 67.4009L215.328 68.5289C216.08 68.0797 216.847 67.3961 217.628 66.4781C218.399 65.5699 219.112 64.4566 219.767 63.1382C220.411 61.8297 220.934 60.3404 221.334 58.6705C221.734 57.0005 221.935 55.189 221.935 53.2359Z" fill="#ABA9A9"/>
<path d="M200.208 29.5273L195.345 44H191.935L198.31 26.9375H200.489L200.208 29.5273ZM204.275 44L199.388 29.5273L199.095 26.9375H201.286L207.696 44H204.275ZM204.052 37.6602V40.2031H194.9V37.6602H204.052Z" fill="black"/>
<path d="M171.364 43.9083V61.0177H168.258V47.5294L164.145 48.8888V46.381L171.012 43.9083H171.364Z" fill="black"/>
<line x1="187.929" y1="46.6207" x2="211.762" y2="46.6207" stroke="#ABA9A9"/>
<path d="M201.288 69.1207H198.17V55.2691C198.17 54.316 198.354 53.5152 198.721 52.8668C199.088 52.2105 199.612 51.7144 200.291 51.3785C200.971 51.0425 201.772 50.8746 202.694 50.8746C202.998 50.8746 203.288 50.8941 203.561 50.9332C203.842 50.9722 204.12 51.0269 204.393 51.0972L204.334 53.4527C204.186 53.4136 204.022 53.3863 203.842 53.3707C203.67 53.355 203.479 53.3472 203.268 53.3472C202.846 53.3472 202.487 53.4214 202.19 53.5699C201.893 53.7183 201.666 53.9371 201.51 54.2261C201.362 54.5074 201.288 54.855 201.288 55.2691V69.1207ZM203.854 56.441V58.6675H196.26V56.441H203.854Z" fill="black"/>
<path d="M204.029 65.9971L204.682 67.5322L205.83 65.9971H206.701L205.006 68.1182L206.037 70.2236H205.268L204.568 68.6416L203.377 70.2236H202.514L204.256 68.0479L203.26 65.9971H204.029Z" fill="#0277BD"/>
<path d="M72.0705 47.6938V50.0845H64.6877V47.6938H72.0705ZM66.5158 44.5649H69.8908V56.5532C69.8908 56.9204 69.9377 57.2017 70.0314 57.397C70.133 57.5923 70.2814 57.729 70.4767 57.8071C70.6721 57.8774 70.9182 57.9126 71.215 57.9126C71.426 57.9126 71.6135 57.9048 71.7775 57.8892C71.9494 57.8657 72.0939 57.8423 72.2111 57.8188L72.2228 60.3032C71.9338 60.397 71.6213 60.4712 71.2853 60.5259C70.9494 60.5806 70.5783 60.6079 70.1721 60.6079C69.4299 60.6079 68.7814 60.4868 68.2267 60.2446C67.6799 59.9946 67.258 59.5962 66.9611 59.0493C66.6642 58.5024 66.5158 57.7837 66.5158 56.8931V44.5649ZM78.2932 60.3735H74.8947V46.5688C74.8947 45.6079 75.0822 44.7993 75.4572 44.1431C75.84 43.479 76.3752 42.979 77.0627 42.6431C77.758 42.2993 78.5822 42.1274 79.5353 42.1274C79.8478 42.1274 80.1486 42.1509 80.4377 42.1978C80.7267 42.2368 81.008 42.2876 81.2814 42.3501L81.2463 44.8931C81.0978 44.854 80.9416 44.8267 80.7775 44.811C80.6135 44.7954 80.4221 44.7876 80.2033 44.7876C79.7971 44.7876 79.4494 44.8579 79.1603 44.9985C78.8791 45.1313 78.6642 45.3306 78.5158 45.5962C78.3674 45.8618 78.2932 46.186 78.2932 46.5688V60.3735ZM80.8244 47.6938V50.0845H73.008V47.6938H80.8244Z" fill="black"/>
<path d="M82.291 59.894L82.9434 61.4291L84.0918 59.894H84.9629L83.2676 62.0151L84.2989 64.1205H83.5293L82.8301 62.5385L81.6387 64.1205H80.7754L82.5176 61.9448L81.5215 59.894H82.291ZM90.2442 63.6088C90.416 63.6114 90.5762 63.5789 90.7246 63.5112C90.8731 63.4435 90.9994 63.3471 91.1035 63.2221C91.2077 63.0971 91.2819 62.9526 91.3262 62.7885L91.9981 62.7846C91.9564 63.0685 91.8457 63.3172 91.666 63.5307C91.489 63.7442 91.2715 63.9109 91.0137 64.0307C90.7585 64.1479 90.4916 64.2039 90.2129 64.1987C89.916 64.1935 89.6634 64.1323 89.4551 64.0151C89.2494 63.8953 89.084 63.7364 88.959 63.5385C88.834 63.3406 88.7481 63.1179 88.7012 62.8705C88.6543 62.6205 88.6439 62.364 88.67 62.101L88.6856 61.933C88.7168 61.6492 88.7858 61.3797 88.8926 61.1245C88.9994 60.8666 89.1413 60.6388 89.3184 60.4409C89.4981 60.2403 89.7103 60.0841 89.9551 59.9721C90.1999 59.8601 90.4746 59.808 90.7793 59.8159C91.0762 59.8211 91.334 59.8914 91.5528 60.0268C91.7715 60.1596 91.9408 60.3406 92.0606 60.5698C92.1804 60.7989 92.2403 61.0593 92.2403 61.351L91.5762 61.3471C91.5736 61.1804 91.541 61.0268 91.4785 60.8862C91.416 60.7455 91.3236 60.6323 91.2012 60.5463C91.0788 60.4604 90.9278 60.4135 90.7481 60.4057C90.5319 60.4005 90.3431 60.4409 90.1817 60.5268C90.0228 60.6127 89.8874 60.7312 89.7754 60.8823C89.666 61.0307 89.5788 61.1961 89.5137 61.3784C89.4512 61.5606 89.4082 61.7455 89.3848 61.933L89.3653 62.0971C89.3496 62.2638 89.347 62.4343 89.3575 62.6088C89.3705 62.7833 89.4069 62.9461 89.4668 63.0971C89.5267 63.2455 89.6192 63.3666 89.7442 63.4604C89.8692 63.5541 90.0358 63.6036 90.2442 63.6088Z" fill="#0277BD"/>
<path d="M85.7754 63.2612L85.6817 63.8393C85.6374 64.1231 85.5371 64.3875 85.3809 64.6323C85.2246 64.8771 85.0332 65.0854 84.8067 65.2573L84.416 64.9643C84.5072 64.8523 84.5905 64.7377 84.666 64.6205C84.7416 64.506 84.8054 64.3849 84.8575 64.2573C84.9121 64.1297 84.9538 63.9955 84.9825 63.8549L85.084 63.2612H85.7754Z" fill="#ABA9A9"/>
<path d="M13.8242 58.3923L17.2227 44.5993H19.0625L19.1797 47.5056L15.5469 61.6618H13.6016L13.8242 58.3923ZM11.6797 44.5993L14.4688 58.3454V61.6618H12.3477L8.48047 44.5993H11.6797ZM22.707 58.2868L25.4492 44.5993H28.6602L24.793 61.6618H22.6719L22.707 58.2868ZM19.9414 44.5993L23.3398 58.4391L23.5391 61.6618H21.5938L17.9727 47.4938L18.1133 44.5993H19.9414Z" fill="black"/>
<path d="M29.2528 60.5382L29.9052 62.0734L31.0536 60.5382H31.9247L30.2294 62.6593L31.2606 64.7648H30.4911L29.7919 63.1827L28.6005 64.7648H27.7372L29.4794 62.589L28.4833 60.5382H29.2528ZM37.2059 64.2531C37.3778 64.2557 37.538 64.2231 37.6864 64.1554C37.8348 64.0877 37.9611 63.9913 38.0653 63.8663C38.1695 63.7413 38.2437 63.5968 38.288 63.4327L38.9598 63.4288C38.9182 63.7127 38.8075 63.9614 38.6278 64.1749C38.4507 64.3885 38.2333 64.5551 37.9755 64.6749C37.7203 64.7921 37.4533 64.8481 37.1747 64.8429C36.8778 64.8377 36.6252 64.7765 36.4169 64.6593C36.2111 64.5395 36.0458 64.3807 35.9208 64.1827C35.7958 63.9848 35.7098 63.7622 35.663 63.5148C35.6161 63.2648 35.6057 63.0083 35.6317 62.7452L35.6473 62.5773C35.6786 62.2934 35.7476 62.0239 35.8544 61.7687C35.9611 61.5109 36.1031 61.283 36.2802 61.0851C36.4598 60.8846 36.6721 60.7283 36.9169 60.6163C37.1617 60.5044 37.4364 60.4523 37.7411 60.4601C38.038 60.4653 38.2958 60.5356 38.5145 60.671C38.7333 60.8038 38.9025 60.9848 39.0223 61.214C39.1421 61.4432 39.202 61.7036 39.202 61.9952L38.538 61.9913C38.5354 61.8247 38.5028 61.671 38.4403 61.5304C38.3778 61.3898 38.2854 61.2765 38.163 61.1906C38.0406 61.1046 37.8895 61.0577 37.7098 61.0499C37.4937 61.0447 37.3049 61.0851 37.1434 61.171C36.9846 61.257 36.8492 61.3754 36.7372 61.5265C36.6278 61.6749 36.5406 61.8403 36.4755 62.0226C36.413 62.2049 36.37 62.3898 36.3466 62.5773L36.327 62.7413C36.3114 62.908 36.3088 63.0786 36.3192 63.2531C36.3322 63.4275 36.3687 63.5903 36.4286 63.7413C36.4885 63.8898 36.5809 64.0109 36.7059 64.1046C36.8309 64.1984 36.9976 64.2478 37.2059 64.2531Z" fill="#0277BD"/>
<path d="M32.7372 63.9054L32.6434 64.4835C32.5992 64.7674 32.4989 65.0317 32.3427 65.2765C32.1864 65.5213 31.995 65.7296 31.7684 65.9015L31.3778 65.6085C31.469 65.4965 31.5523 65.382 31.6278 65.2648C31.7033 65.1502 31.7671 65.0291 31.8192 64.9015C31.8739 64.7739 31.9156 64.6398 31.9442 64.4991L32.0458 63.9054H32.7372Z" fill="#ABA9A9"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 13 KiB

LLMTopicDetection_BERTopic/docs/algorithm/6. diversity.svg
+11
View File
File diff suppressed because one or more lines are too long
Side by Side

After

Width:  |  Height:  |  Size: 55 KiB

LLMTopicDetection_BERTopic/docs/algorithm/algorithm.md
+175
View File
@@ -0,0 +1,175 @@
---
hide:
- navigation
---
# The Algorithm
Below, you will find different types of overviews of each step in BERTopic's main algorithm. Each successive overview will be more in-depth than the previous overview. This approach aims to make the underlying algorithm as intuitive as possible for a wide range of users.
## **Visual Overview**
BERTopic can be viewed as a sequence of steps to create its topic representations. There are five steps to this process:
<img src="default.svg">
Although these steps are the default, there is some modularity to BERTopic. Each step in this process was carefully selected such that they are all somewhat independent from one another. For example, the tokenization step is not directly influenced by the embedding model that was used to convert the documents which allow us to be creative in how we perform the tokenization step.
This effect is especially strong in the clustering step. Models like HDBSCAN assume that clusters can have different shapes and forms. As a result, using a centroid-based technique to model the topic representations would not be beneficial since the centroid is not always representative of these types of clusters. A bag-of-words representation, however, makes very few assumptions concerning the shape and form of a cluster.
As a result, BERTopic is quite modular and can maintain its quality of topic generation throughout a variety of sub-models. In other words, BERTopic essentially allows you to **build your own topic model**:
<img src="modularity.svg">
There is extensive documentation on how to use each step in this pipeline:
1. [Embeddings](../getting_started/embeddings/embeddings.html)
2. [Dimensionality Reduction](../getting_started/dim_reduction/dim_reduction.html)
3. [Clustering](../getting_started/clustering/clustering.html)
4. [Tokenizer](../getting_started/vectorizers/vectorizers.html)
5. [Weighting Scheme](../getting_started/ctfidf/ctfidf.html)
6. [Representation Tuning](../getting_started/representation/representation.html)
* [Large Language Models (LLM)](../getting_started/representation/llm.html)
## **Code Overview**
After going through the visual overview, this code overview demonstrates the algorithm using BERTopic. An advantage of using BERTopic is each major step in its algorithm can be explicitly defined, thereby making the process not only transparent but also more intuitive.
```python
from umap import UMAP
from hdbscan import HDBSCAN
from sentence_transformers import SentenceTransformer
from sklearn.feature_extraction.text import CountVectorizer
from bertopic import BERTopic
from bertopic.representation import KeyBERTInspired
from bertopic.vectorizers import ClassTfidfTransformer
# Step 1 - Extract embeddings
embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
# Step 2 - Reduce dimensionality
umap_model = UMAP(n_neighbors=15, n_components=5, min_dist=0.0, metric='cosine')
# Step 3 - Cluster reduced embeddings
hdbscan_model = HDBSCAN(min_cluster_size=15, metric='euclidean', cluster_selection_method='eom', prediction_data=True)
# Step 4 - Tokenize topics
vectorizer_model = CountVectorizer(stop_words="english")
# Step 5 - Create topic representation
ctfidf_model = ClassTfidfTransformer()
# Step 6 - (Optional) Fine-tune topic representations with
# a `bertopic.representation` model
representation_model = KeyBERTInspired()
# All steps together
topic_model = BERTopic(
embedding_model=embedding_model, # Step 1 - Extract embeddings
umap_model=umap_model, # Step 2 - Reduce dimensionality
hdbscan_model=hdbscan_model, # Step 3 - Cluster reduced embeddings
vectorizer_model=vectorizer_model, # Step 4 - Tokenize topics
ctfidf_model=ctfidf_model, # Step 5 - Extract topic words
representation_model=representation_model # Step 6 - (Optional) Fine-tune topic representations
)
```
## **Detailed Overview**
This overview describes each step in more detail such that you can get an intuitive feeling as to what models might fit best at each step in your use case.
### **1. Embed documents**
We start by converting our documents to numerical representations. Although there are many methods for doing so the default in BERTopic is [sentence-transformers](https://github.com/UKPLab/sentence-transformers). These models are often optimized for semantic similarity which helps tremendously in our clustering task. Moreover, they are great for creating either document- or sentence-embeddings.
<br>
In BERTopic, you can choose any sentence-transformers model but two models are set as defaults:
* `"all-MiniLM-L6-v2"`
* `"paraphrase-multilingual-MiniLM-L12-v2"`
The first is an English language model trained specifically for semantic similarity tasks which works quite
well for most use cases. The second model is very similar to the first with one major difference being that the
`multilingual` models work for 50+ languages. This model is quite a bit larger than the first and is only selected if
you select any language other than English.
!!! tip Embedding models
Although BERTopic uses sentence-transformers models as a default, you can choose
any embedding model that fits your use case. Follow the guide [here](https://maartengr.github.io/BERTopic/getting_started/embeddings/embeddings.html) for selecting
and customizing your model.
### **2. Dimensionality reduction**
After having created our numerical representations of the documents we have to reduce the dimensionality of these representations. Cluster models typically have difficulty handling high dimensional data due to the curse of dimensionality. There are great approaches that can reduce dimensionality, such as PCA, but as a default [UMAP](https://github.com/lmcinnes/umap) is selected in BERTopic. It is a technique that can keep some of a dataset's local and global structure when reducing its dimensionality. This structure is important to keep as it contains the information necessary to create clusters of semantically similar documents.
!!! tip Dimensionality reduction models
Although BERTopic uses UMAP as a default, you can choose
any dimensionality reduction model that fits your use case. Follow the guide [here](https://maartengr.github.io/BERTopic/getting_started/dim_reduction/dim_reduction.html) for selecting
and customizing your model.
### **3. Cluster Documents**
After having reduced our embeddings, we can start clustering our data. For that, we leverage a density-based clustering technique, HDBSCAN. It can find clusters of different shapes and has the nice feature of identifying outliers where possible. As a result, we do not force documents into a cluster where they might not belong. This will improve the resulting topic representation as there is less noise to draw from.
!!! tip Cluster models
Although BERTopic uses HDBSCAN as a default, you can choose
any cluster model that fits your use case. Follow the guide [here](https://maartengr.github.io/BERTopic/getting_started/clustering/clustering.html) for selecting
and customizing your model.
### **4. Bag-of-words**
Before we can start creating the topic representation we first need to select a technique that allows for modularity in BERTopic's algorithm. When we use HDBSCAN as a cluster model, we may assume that our clusters have different degrees of density and different shapes. This means that a centroid-based topic representation technique might not be the best-fitting model. In other words, we want a topic representation technique that makes little to no assumption on the expected structure of the clusters.
<br>
To do this, we first combine all documents in a cluster into a single document. That, very long, document then represents the cluster. Then, we can count how often each word appears in each cluster. This generates something called a bag-of-words representation in which the frequency of each word in each cluster can be found. This bag-of-words representation is therefore on a cluster level and not on a document level. This distinction is important as we are interested in words on a topic level (i.e., cluster level). By using a bag-of-words representation, no assumption is made concerning the structure of the clusters. Moreover, the bag-of-words representation is L1-normalized to account for clusters that have different sizes.
!!! tip Bag-of-words and tokenization
There are many ways you can tune or change the bag-of-words step. This step allows for processing the documents however you want without affecting the first step, embedding the documents. You can follow the guide [here](https://maartengr.github.io/BERTopic/getting_started/vectorizers/vectorizers.html) for more information about tokenization options in BERTopic.
### **5. Topic representation**
From the generated bag-of-words representation, we want to know what makes one cluster different from another. Which words are typical for cluster 1 and not so much for all other clusters? To solve this, we need to modify TF-IDF such that it considers topics (i.e., clusters) instead of documents.
<br>
When you apply TF-IDF as usual on a set of documents, what you are doing is comparing the importance of
words between documents. Now, what if, we instead treat all documents in a single category (e.g., a cluster) as a single document and then apply TF-IDF? The result would be importance scores for words within a cluster. The more important words are within a cluster, the more it is representative of that topic. In other words, if we extract the most important words per cluster, we get descriptions of **topics**! This model is called **class-based TF-IDF**:
<br><br>
<img class="w-6/12" src="c-TF-IDF.svg">
<br>
Each cluster is converted to a single document instead of a set of documents. Then, we extract the frequency of word `x` in class `c`, where `c` refers to the cluster we created before. This results in our class-based `tf` representation. This representation is L1-normalized to account for the differences in topic sizes.
<br><br>
Then, we take the logarithm of one plus the average number of words per class `A` divided by the frequency of word `x` across all classes. We add plus one within the logarithm to force values to be positive. This results in our class-based `idf` representation. Like with the classic TF-IDF, we then multiply `tf` with `idf` to get the importance score per word in each class. In other words, the classical TF-IDF procedure is **not** used here but a modified version of the algorithm that allows for a much better representation.
!!! tip c-TF-IDF parameters
In the `ClassTfidfTransformer`, there are a few parameters that might be worth exploring, including an option to perform additional BM-25 weighting. You can find more information about that [here](https://maartengr.github.io/BERTopic/getting_started/ctfidf/ctfidf.html).
### **6. (Optional) Fine-tune Topic representation**
After having generated the c-TF-IDF representations, we have a set of words that describe a collection of documents. c-TF-IDF
is a method that can quickly generate accurate topic representations. However, with the fast developments in NLP-world, new
and exciting methods are released weekly. In order to keep up with what is happening, there is the possibility to further fine-tune
these c-TF-IDF topics using GPT, T5, KeyBERT, Spacy, and other techniques. Many are implemented in BERTopic for you to use and play around with.
More specifically, we can consider the c-TF-IDF generated topics to be candidate topics. They each contain a set of keywords and
representative documents that we can use to further fine-tune the topic representations. Having a set of representative documents
for each topic is huge advantage as it allows for fine-tuning on a reduced number of documents. This reduces computation for
large models as they only need to operate on that small set of representative documents for each topic. As a result,
large language models like GPT and T5 becomes feasible in production settings and typically take less wall time than the dimensionality reduction
and clustering steps.
The following models are implemented in `bertopic.representation`:
* `MaximalMarginalRelevance`
* `PartOfSpeech`
* `KeyBERTInspired`
* `ZeroShotClassification`
* `TextGeneration` (HuggingFace)
* `Cohere`
* `OpenAI`
* `LangChain`
* `LiteLLM`
* `LlamaCPP`
!!! tip Models
There are roughly two sets of models. **First** are the non-generative set of models that you can find [here](https://maartengr.github.io/BERTopic/getting_started/representation/representation.html). These include models that focus on enhancing the keywords in the topic representations. **Second** are the generative models that attempt to label or summarize the topics instead. You can find an overview of [implemented LLMs here](https://maartengr.github.io/BERTopic/getting_started/representation/llm).
LLMTopicDetection_BERTopic/docs/algorithm/c-TF-IDF.svg
+37
View File
File diff suppressed because one or more lines are too long
Side by Side

After

Width:  |  Height:  |  Size: 138 KiB

LLMTopicDetection_BERTopic/docs/algorithm/default.svg
+49
View File
@@ -0,0 +1,49 @@
<svg width="320" height="252" viewBox="0 0 320 252" fill="none" xmlns="http://www.w3.org/2000/svg">
<rect x="202" y="210" width="118" height="38" fill="#64B5F6"/>
<rect x="294" y="200" width="20" height="8" fill="#64B5F6"/>
<rect x="266" y="200" width="20" height="8" fill="#64B5F6"/>
<rect x="238" y="200" width="20" height="8" fill="#64B5F6"/>
<rect x="210" y="200" width="20" height="8" fill="#64B5F6"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="228.256" y="237.939">SBERT</tspan></text>
<rect x="202" y="170" width="118" height="38" fill="#E57373"/>
<rect x="294" y="160" width="20" height="8" fill="#E57373"/>
<rect x="266" y="160" width="20" height="8" fill="#E57373"/>
<rect x="238" y="160" width="20" height="8" fill="#E57373"/>
<rect x="210" y="160" width="20" height="8" fill="#E57373"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="231.254" y="197.939">UMAP</tspan></text>
<rect x="202" y="130" width="118" height="38" fill="#4DB6AC"/>
<rect x="294" y="120" width="20" height="8" fill="#4DB6AC"/>
<rect x="266" y="120" width="20" height="8" fill="#4DB6AC"/>
<rect x="238" y="120" width="20" height="8" fill="#4DB6AC"/>
<rect x="210" y="120" width="20" height="8" fill="#4DB6AC"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="211.342" y="157.939">HDBSCAN</tspan></text>
<rect x="202" y="90" width="118" height="38" fill="#FFD54F"/>
<rect x="294" y="80" width="20" height="8" fill="#FFD54F"/>
<rect x="266" y="80" width="20" height="8" fill="#FFD54F"/>
<rect x="238" y="80" width="20" height="8" fill="#FFD54F"/>
<rect x="210" y="80" width="20" height="8" fill="#FFD54F"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="13" font-weight="bold" letter-spacing="0em"><tspan x="208.346" y="113.161">CountVectorizer</tspan></text>
<rect x="202" y="50" width="118" height="38" fill="#90A4AE"/>
<rect x="294" y="40" width="20" height="8" fill="#90A4AE"/>
<rect x="266" y="40" width="20" height="8" fill="#90A4AE"/>
<rect x="238" y="40" width="20" height="8" fill="#90A4AE"/>
<rect x="210" y="40" width="20" height="8" fill="#90A4AE"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="216.938" y="77.9395">c-TF-IDF</tspan></text>
<rect x="202" y="10" width="118" height="38" fill="#3F51B5"/>
<rect x="294" width="20" height="8" fill="#3F51B5"/>
<rect x="266" width="20" height="8" fill="#3F51B5"/>
<rect x="238" width="20" height="8" fill="#3F51B5"/>
<rect x="210" width="20" height="8" fill="#3F51B5"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="14" font-weight="bold" letter-spacing="0em"><tspan x="231.065" y="25.0576">Optional&#10;</tspan><tspan x="220.271" y="42.0576">Fine-tuning</tspan></text>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="85.4023" y="65.7637">Weighting scheme</tspan></text>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="138.938" y="111.764">Tokenizer</tspan></text>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="136.312" y="153.764">Clustering</tspan></text>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="43.1602" y="193.764">Dimensionality Reduction</tspan></text>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="124.301" y="233.764">Embeddings</tspan></text>
<path d="M169.354 203.646C169.158 203.451 168.842 203.451 168.646 203.646L165.464 206.828C165.269 207.024 165.269 207.34 165.464 207.536C165.66 207.731 165.976 207.731 166.172 207.536L169 204.707L171.828 207.536C172.024 207.731 172.34 207.731 172.536 207.536C172.731 207.34 172.731 207.024 172.536 206.828L169.354 203.646ZM169.5 218L169.5 204L168.5 204L168.5 218L169.5 218Z" fill="black"/>
<path d="M169.354 75.6464C169.158 75.4512 168.842 75.4512 168.646 75.6464L165.464 78.8284C165.269 79.0237 165.269 79.3403 165.464 79.5355C165.66 79.7308 165.976 79.7308 166.172 79.5355L169 76.7071L171.828 79.5355C172.024 79.7308 172.34 79.7308 172.536 79.5355C172.731 79.3403 172.731 79.0237 172.536 78.8284L169.354 75.6464ZM169.5 90L169.5 76L168.5 76L168.5 90L169.5 90Z" fill="black"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="36.6289" y="25.7637">Fine-tune Representations</tspan></text>
<path d="M169.354 35.6464C169.158 35.4512 168.842 35.4512 168.646 35.6464L165.464 38.8284C165.269 39.0237 165.269 39.3403 165.464 39.5355C165.66 39.7308 165.976 39.7308 166.172 39.5355L169 36.7071L171.828 39.5355C172.024 39.7308 172.34 39.7308 172.536 39.5355C172.731 39.3403 172.731 39.0237 172.536 38.8284L169.354 35.6464ZM169.5 50L169.5 36L168.5 36L168.5 50L169.5 50Z" fill="black"/>
<path d="M169.354 120.646C169.158 120.451 168.842 120.451 168.646 120.646L165.464 123.828C165.269 124.024 165.269 124.34 165.464 124.536C165.66 124.731 165.976 124.731 166.172 124.536L169 121.707L171.828 124.536C172.024 124.731 172.34 124.731 172.536 124.536C172.731 124.34 172.731 124.024 172.536 123.828L169.354 120.646ZM169.5 135L169.5 121L168.5 121L168.5 135L169.5 135Z" fill="black"/>
<path d="M169.354 162.646C169.158 162.451 168.842 162.451 168.646 162.646L165.464 165.828C165.269 166.024 165.269 166.34 165.464 166.536C165.66 166.731 165.976 166.731 166.172 166.536L169 163.707L171.828 166.536C172.024 166.731 172.34 166.731 172.536 166.536C172.731 166.34 172.731 166.024 172.536 165.828L169.354 162.646ZM169.5 177L169.5 163L168.5 163L168.5 177L169.5 177Z" fill="black"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 6.2 KiB

LLMTopicDetection_BERTopic/docs/algorithm/modularity.svg
+257
View File
@@ -0,0 +1,257 @@
<svg width="992" height="452" viewBox="0 0 992 452" fill="none" xmlns="http://www.w3.org/2000/svg">
<circle cx="803.5" cy="229.5" r="5.5" fill="black"/>
<circle cx="823.5" cy="229.5" r="5.5" fill="black"/>
<circle cx="843.5" cy="229.5" r="5.5" fill="black"/>
<rect x="121" y="411" width="118" height="38" fill="#64B5F6"/>
<rect x="213" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="185" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="157" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="129" y="401" width="20" height="8" fill="#64B5F6"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="147.256" y="438.939">SBERT</tspan></text>
<rect x="253" y="411" width="118" height="38" fill="#64B5F6"/>
<rect x="345" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="317" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="289" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="261" y="401" width="20" height="8" fill="#64B5F6"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="280.936" y="438.939">SpaCy</tspan></text>
<rect x="448" y="411" width="118" height="38" fill="#64B5F6"/>
<rect x="540" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="512" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="484" y="401" width="20" height="8" fill="#64B5F6"/>
<rect x="456" y="401" width="20" height="8" fill="#64B5F6"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="479.623" y="433.764">Transformers</tspan></text>
<circle cx="387.5" cy="429.5" r="5.5" fill="black"/>
<circle cx="406.5" cy="429.5" r="5.5" fill="black"/>
<circle cx="428.5" cy="429.5" r="5.5" fill="black"/>
<path d="M466.944 437.706C463.02 437.706 458.787 435.245 458.787 429.845C458.787 424.445 463.02 421.984 466.944 421.984C469.123 421.984 471.134 422.702 472.625 424.009C474.242 425.444 475.1 427.469 475.1 429.845C475.1 432.222 474.242 434.233 472.625 435.667C471.134 436.975 469.109 437.706 466.944 437.706Z" fill="url(#paint0_radial_31_1943)"/>
<path d="M466.944 437.706C463.02 437.706 458.787 435.245 458.787 429.845C458.787 424.445 463.02 421.984 466.944 421.984C469.123 421.984 471.134 422.702 472.625 424.009C474.242 425.444 475.1 427.469 475.1 429.845C475.1 432.222 474.242 434.233 472.625 435.667C471.134 436.975 469.109 437.706 466.944 437.706Z" fill="url(#paint1_linear_31_1943)"/>
<path d="M473.678 425.172C474.428 426.382 474.819 427.822 474.819 429.423C474.819 431.8 473.961 433.811 472.344 435.245C470.853 436.553 468.828 437.284 466.663 437.284C464.123 437.284 461.454 436.251 459.887 434.058C461.4 436.542 464.245 437.706 466.944 437.706C469.109 437.706 471.134 436.975 472.625 435.667C474.242 434.233 475.1 432.222 475.1 429.845C475.1 428.054 474.612 426.462 473.678 425.172V425.172Z" fill="#EB8F00"/>
<path opacity="0.8" d="M462.177 432.306C463.443 432.306 464.469 431.28 464.469 430.014C464.469 428.748 463.443 427.722 462.177 427.722C460.911 427.722 459.884 428.748 459.884 430.014C459.884 431.28 460.911 432.306 462.177 432.306Z" fill="url(#paint2_radial_31_1943)"/>
<path opacity="0.8" d="M471.627 430.534C472.893 430.534 473.919 429.508 473.919 428.242C473.919 426.976 472.893 425.95 471.627 425.95C470.361 425.95 469.334 426.976 469.334 428.242C469.334 429.508 470.361 430.534 471.627 430.534Z" fill="url(#paint3_radial_31_1943)"/>
<path d="M471.627 427.947C470.544 428.945 469.109 429.733 467.45 430.113C465.791 430.492 464.159 430.422 462.753 429.986C462.5 429.902 462.317 430.239 462.542 430.408C463.962 431.463 465.861 431.913 467.759 431.463C469.658 431.027 471.177 429.803 471.992 428.228C472.133 427.989 471.823 427.764 471.627 427.947V427.947Z" fill="#422B0D"/>
<path d="M464.82 427.638L464.792 427.609C464.778 427.595 464.75 427.581 464.722 427.553C464.694 427.539 464.666 427.511 464.637 427.497C464.609 427.469 464.567 427.441 464.525 427.413C464.483 427.384 464.441 427.356 464.398 427.342C464.356 427.314 464.314 427.3 464.272 427.3C464.23 427.286 464.202 427.286 464.187 427.286H464.159H464.145H464.173L464.103 427.3C464.089 427.3 464.103 427.3 464.103 427.3H464.117C464.131 427.3 464.117 427.3 464.117 427.3H464.103C464.089 427.314 464.061 427.328 464.033 427.342C464.005 427.37 463.962 427.398 463.934 427.427C463.906 427.455 463.878 427.497 463.85 427.539C463.794 427.623 463.752 427.694 463.723 427.75C463.695 427.806 463.667 427.834 463.667 427.834L463.639 427.891C463.498 428.13 463.189 428.228 462.936 428.102C462.767 428.017 462.669 427.863 462.655 427.694V427.539C462.669 427.441 462.683 427.3 462.739 427.131C462.795 426.963 462.894 426.752 463.077 426.555C463.175 426.456 463.287 426.344 463.428 426.273C463.456 426.245 463.498 426.231 463.541 426.217C463.583 426.203 463.611 426.175 463.667 426.161L463.737 426.133C463.766 426.119 463.794 426.119 463.808 426.119L463.878 426.105L463.92 426.091H463.977L464.047 426.077H464.173C464.258 426.077 464.342 426.077 464.427 426.091C464.595 426.119 464.736 426.175 464.862 426.231C465.116 426.358 465.27 426.513 465.397 426.639C465.453 426.709 465.509 426.766 465.537 426.822C465.58 426.878 465.608 426.934 465.636 426.977C465.664 427.019 465.664 427.047 465.678 427.061C465.678 427.075 465.692 427.089 465.692 427.089C465.791 427.342 465.65 427.623 465.369 427.722C465.172 427.792 464.961 427.75 464.82 427.638V427.638Z" fill="#422B0D"/>
<path d="M469.644 426.695L469.616 426.667C469.602 426.653 469.573 426.639 469.545 426.611C469.517 426.597 469.489 426.569 469.461 426.555C469.433 426.527 469.391 426.498 469.348 426.47C469.306 426.442 469.264 426.414 469.222 426.4C469.18 426.372 469.137 426.358 469.095 426.358C469.067 426.344 469.039 426.344 469.025 426.344H468.983H469.011L468.941 426.358C468.927 426.358 468.941 426.358 468.941 426.358H468.955C468.969 426.358 468.955 426.358 468.955 426.358H468.941C468.927 426.372 468.898 426.386 468.856 426.4C468.828 426.428 468.8 426.456 468.758 426.484C468.73 426.513 468.702 426.555 468.673 426.597C468.617 426.681 468.575 426.752 468.547 426.808C468.519 426.864 468.491 426.892 468.491 426.892L468.462 426.934C468.322 427.173 468.012 427.272 467.759 427.145C467.591 427.061 467.492 426.906 467.478 426.738C467.478 426.738 467.478 426.681 467.492 426.583C467.506 426.484 467.52 426.344 467.577 426.175C467.633 426.006 467.731 425.795 467.914 425.598C468.012 425.5 468.125 425.388 468.266 425.317C468.294 425.303 468.336 425.275 468.378 425.261C468.42 425.247 468.448 425.219 468.505 425.205L468.589 425.177C468.617 425.163 468.645 425.163 468.659 425.163L468.73 425.148L468.772 425.134H468.828L468.898 425.12H469.025C469.109 425.12 469.194 425.12 469.278 425.134C469.447 425.163 469.587 425.219 469.714 425.275C469.967 425.402 470.122 425.556 470.248 425.683C470.305 425.753 470.361 425.809 470.389 425.866C470.431 425.922 470.459 425.978 470.487 426.02C470.516 426.063 470.516 426.091 470.53 426.105C470.544 426.119 470.544 426.133 470.544 426.133C470.642 426.386 470.502 426.667 470.22 426.766C469.995 426.864 469.784 426.822 469.644 426.695V426.695Z" fill="#422B0D"/>
<path d="M464.029 432.62C463.993 432.27 464.009 432.07 463.74 432.007C463.439 431.936 463.171 432.152 463.089 432.46C462.874 433.284 463.24 433.859 463.24 433.859C462.719 433.756 462.285 433.25 462.285 433.25C462.013 432.931 461.631 432.137 461.367 431.811C461.206 431.613 460.943 431.451 460.682 431.588C460.055 431.917 460.749 433.036 460.983 433.334C461.248 433.673 460.292 432.589 460.152 432.353C459.89 431.914 459.569 431.797 459.301 432.026C459.032 432.254 459.247 432.824 459.37 433.04C460.119 434.355 460.773 434.677 460.773 434.677C460.773 434.677 460.077 434.342 459.484 433.624C458.924 432.946 458.392 433.662 458.765 434.264C458.844 434.392 458.994 434.722 459.478 435.14C459.849 435.46 459.607 435.268 459.478 435.14C458.983 434.652 458.456 435.172 458.615 435.598C458.799 436.089 459.399 436.543 459.806 436.844C460.596 437.429 461.582 437.897 462.58 437.865C463.691 437.83 464.511 437.367 464.757 435.993C464.871 435.355 464.515 434.376 464.41 434.126C464.065 433.316 464.048 432.818 464.029 432.62Z" fill="url(#paint4_radial_31_1943)"/>
<path d="M462.913 436.038C462.764 435.829 462.344 434.856 463.129 433.86L463.356 434.004C462.468 435.1 463.089 436.037 463.197 436.249C463.197 436.249 463.055 436.24 462.913 436.038V436.038Z" fill="#EB8F00"/>
<path d="M464.497 434.036C464.148 433.36 464.123 433.008 464.099 432.623C464.072 432.344 464.052 432 463.716 431.921C463.573 431.887 463.373 431.907 463.196 432.102C462.753 432.595 463.106 433.739 463.106 433.739C462.469 433.441 462.362 433.178 461.911 432.499C461.714 432.201 461.4 431.65 461.113 431.489C460.908 431.374 460.604 431.46 460.452 431.665C460.111 432.123 460.72 433.053 460.72 433.053C460.72 433.053 460.384 432.564 460.237 432.308C459.988 431.873 459.533 431.633 459.197 431.935C458.648 432.429 459.714 433.756 459.714 433.756C459.714 433.756 459.223 432.978 458.734 433.307C458.48 433.479 458.38 433.926 458.644 434.357C458.761 434.552 459.057 434.898 459.057 434.898C459.057 434.898 458.938 434.822 458.738 434.887C458.516 434.96 458.326 435.235 458.488 435.666C458.675 436.169 459.229 436.605 459.734 436.969C460.883 437.799 462.226 437.85 462.226 437.85C462.226 437.85 460.753 437.567 459.811 436.709C459.516 436.441 458.346 435.624 458.764 435.199C458.862 435.098 459.042 435.047 459.308 435.258C460.243 436.003 460.562 435.83 460.562 435.83C460.596 435.701 460.503 435.646 460.225 435.482C460.032 435.368 459.768 435.212 459.572 435.044C459.093 434.629 458.551 433.908 458.848 433.587C459.007 433.416 459.191 433.452 459.37 433.637C460.613 434.905 460.905 434.726 460.905 434.726C460.905 434.726 460.943 434.589 460.551 434.244C460.25 433.981 459.88 433.656 459.423 432.86C459.302 432.649 459.24 432.274 459.417 432.126C459.657 431.924 459.877 432.057 460.076 432.354C460.317 432.715 460.661 433.16 461.002 433.487C461.416 433.883 461.638 434.004 461.652 433.99C461.75 433.883 461.327 433.468 461.139 433.209C460.475 432.294 460.485 431.993 460.623 431.755C460.71 431.605 460.95 431.537 461.24 431.901C461.864 432.621 462.179 433.793 463.355 434.001C463.355 434.001 463.4 433.93 463.295 433.549C463.168 433.151 463.147 432.812 463.212 432.516C463.283 432.188 463.546 432.095 463.691 432.13C463.885 432.177 463.863 432.503 463.863 432.503C463.863 432.503 463.874 432.623 463.88 432.677C463.902 432.914 463.948 433.406 464.275 434.165C464.405 434.469 465.103 435.718 464.158 437.28C464.158 437.28 464.559 437.383 465.019 437.49C465.019 437.49 465.2 436.85 465.116 435.856C465.013 434.605 464.732 434.492 464.497 434.036V434.036Z" fill="#EB8F00"/>
<path d="M458.077 435.438C458.082 435.399 458.087 435.365 458.094 435.335C458.084 435.368 458.079 435.401 458.077 435.438Z" fill="url(#paint5_radial_31_1943)"/>
<path d="M469.843 432.62C469.879 432.27 469.865 432.077 470.132 432.007C470.419 431.932 470.696 432.153 470.783 432.46C470.984 433.18 470.599 433.859 470.599 433.859C471.119 433.756 471.56 433.257 471.56 433.257C471.832 432.938 472.242 432.137 472.505 431.811C472.666 431.613 472.856 431.485 473.131 431.586C473.701 431.797 473.106 432.95 472.872 433.25C472.607 433.589 472.775 433.534 473.133 433.142C473.491 432.746 473.681 432.523 473.822 432.288C474.083 431.849 474.397 431.883 474.571 432.026C474.844 432.251 474.625 432.824 474.502 433.04C473.753 434.355 474.388 433.624 474.388 433.624C474.948 432.946 475.48 433.662 475.107 434.264C475.028 434.392 474.878 434.722 474.394 435.14C474.023 435.46 474.265 435.268 474.394 435.14C474.889 434.652 475.416 435.172 475.257 435.598C475.073 436.089 474.473 436.543 474.066 436.844C473.276 437.429 472.29 437.897 471.292 437.865C470.181 437.83 469.361 437.367 469.115 435.993C469.001 435.355 469.357 434.376 469.462 434.126C469.807 433.316 469.824 432.818 469.843 432.62V432.62Z" fill="url(#paint6_radial_31_1943)"/>
<path d="M470.959 436.038C471.108 435.829 471.528 434.856 470.743 433.86L470.516 434.004C471.404 435.1 470.783 436.037 470.675 436.249C470.675 436.249 470.817 436.24 470.959 436.038V436.038Z" fill="#EB8F00"/>
<path d="M469.375 434.036C469.724 433.36 469.749 433.008 469.773 432.623C469.8 432.344 469.82 432 470.156 431.921C470.299 431.887 470.499 431.907 470.676 432.102C471.119 432.595 470.766 433.739 470.766 433.739C471.403 433.441 471.51 433.178 471.961 432.499C472.158 432.201 472.472 431.65 472.759 431.489C472.964 431.374 473.268 431.46 473.42 431.665C473.761 432.123 473.152 433.053 473.152 433.053C473.152 433.053 473.488 432.564 473.635 432.308C473.884 431.873 474.339 431.633 474.675 431.935C475.224 432.429 474.158 433.756 474.158 433.756C474.158 433.756 474.649 432.978 475.138 433.307C475.392 433.479 475.492 433.926 475.228 434.357C475.111 434.552 474.815 434.898 474.815 434.898C474.815 434.898 474.934 434.822 475.134 434.887C475.356 434.96 475.546 435.235 475.384 435.666C475.197 436.169 474.643 436.605 474.138 436.969C472.989 437.799 471.646 437.85 471.646 437.85C471.646 437.85 473.119 437.567 474.061 436.709C474.356 436.441 475.526 435.624 475.108 435.199C475.01 435.098 474.83 435.047 474.564 435.258C473.629 436.003 473.31 435.83 473.31 435.83C473.276 435.701 473.369 435.646 473.647 435.482C473.84 435.368 474.104 435.212 474.3 435.044C474.779 434.629 475.321 433.908 475.024 433.587C474.865 433.416 474.681 433.452 474.502 433.637C473.259 434.905 472.967 434.726 472.967 434.726C472.967 434.726 472.929 434.589 473.321 434.244C473.622 433.981 473.992 433.656 474.449 432.86C474.57 432.649 474.632 432.274 474.455 432.126C474.215 431.924 473.995 432.057 473.796 432.354C473.555 432.715 473.211 433.16 472.87 433.487C472.456 433.883 472.234 434.004 472.22 433.99C472.122 433.883 472.545 433.468 472.733 433.209C473.397 432.294 473.387 431.993 473.249 431.755C473.162 431.605 472.922 431.537 472.632 431.901C472.005 432.624 471.69 433.795 470.516 434.004C470.516 434.004 470.471 433.933 470.576 433.552C470.703 433.154 470.724 432.815 470.659 432.519C470.587 432.191 470.324 432.098 470.18 432.133C469.985 432.18 470.008 432.506 470.008 432.506C470.008 432.506 469.997 432.625 469.991 432.68C469.969 432.917 469.922 433.409 469.596 434.168C469.465 434.472 468.766 435.733 469.713 437.283C469.713 437.283 469.312 437.386 468.852 437.492C468.852 437.492 468.671 436.853 468.755 435.858C468.859 434.605 469.14 434.492 469.375 434.036V434.036Z" fill="#EB8F00"/>
<path d="M475.795 435.438C475.79 435.399 475.785 435.365 475.778 435.335C475.788 435.368 475.793 435.401 475.795 435.438Z" fill="url(#paint7_radial_31_1943)"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="29.3008" y="432.764">Embeddings</tspan></text>
<rect x="121" y="331" width="118" height="38" fill="#E57373"/>
<rect x="213" y="321" width="20" height="8" fill="#E57373"/>
<rect x="185" y="321" width="20" height="8" fill="#E57373"/>
<rect x="157" y="321" width="20" height="8" fill="#E57373"/>
<rect x="129" y="321" width="20" height="8" fill="#E57373"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="150.254" y="358.939">UMAP</tspan></text>
<rect x="253" y="331" width="118" height="38" fill="#E57373"/>
<rect x="345" y="321" width="20" height="8" fill="#E57373"/>
<rect x="317" y="321" width="20" height="8" fill="#E57373"/>
<rect x="289" y="321" width="20" height="8" fill="#E57373"/>
<rect x="261" y="321" width="20" height="8" fill="#E57373"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="291.902" y="358.939">PCA</tspan></text>
<rect x="448" y="331" width="118" height="38" fill="#E57373"/>
<rect x="540" y="321" width="20" height="8" fill="#E57373"/>
<rect x="512" y="321" width="20" height="8" fill="#E57373"/>
<rect x="484" y="321" width="20" height="8" fill="#E57373"/>
<rect x="456" y="321" width="20" height="8" fill="#E57373"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="14" font-weight="bold" letter-spacing="0em"><tspan x="456.886" y="356.058">TruncatedSVD</tspan></text>
<circle cx="387.5" cy="349.5" r="5.5" fill="black"/>
<circle cx="407.5" cy="349.5" r="5.5" fill="black"/>
<circle cx="427.5" cy="349.5" r="5.5" fill="black"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="12.8008" y="346.764">Dimensionality&#10;</tspan><tspan x="41.875" y="360.764">Reduction</tspan></text>
<rect x="121" y="251" width="118" height="38" fill="#4DB6AC"/>
<rect x="213" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="185" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="157" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="129" y="241" width="20" height="8" fill="#4DB6AC"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="130.342" y="278.939">HDBSCAN</tspan></text>
<rect x="253" y="251" width="118" height="38" fill="#4DB6AC"/>
<rect x="345" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="317" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="289" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="261" y="241" width="20" height="8" fill="#4DB6AC"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="269.246" y="278.939">k-Means</tspan></text>
<rect x="448" y="251" width="118" height="38" fill="#4DB6AC"/>
<rect x="540" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="512" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="484" y="241" width="20" height="8" fill="#4DB6AC"/>
<rect x="456" y="241" width="20" height="8" fill="#4DB6AC"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="472.709" y="278.939">BIRCH</tspan></text>
<circle cx="387.5" cy="269.5" r="5.5" fill="black"/>
<circle cx="407.5" cy="269.5" r="5.5" fill="black"/>
<circle cx="427.5" cy="269.5" r="5.5" fill="black"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="41.3125" y="273.764">Clustering</tspan></text>
<rect x="121" y="171" width="118" height="38" fill="#FFD54F"/>
<rect x="213" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="185" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="157" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="129" y="161" width="20" height="8" fill="#FFD54F"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="13" font-weight="bold" letter-spacing="0em"><tspan x="127.346" y="195.161">CountVectorizer</tspan></text>
<rect x="253" y="171" width="118" height="38" fill="#FFD54F"/>
<rect x="345" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="317" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="289" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="261" y="161" width="20" height="8" fill="#FFD54F"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="285.73" y="198.939">Jieba</tspan></text>
<rect x="448" y="171" width="118" height="38" fill="#FFD54F"/>
<rect x="540" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="512" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="484" y="161" width="20" height="8" fill="#FFD54F"/>
<rect x="456" y="161" width="20" height="8" fill="#FFD54F"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="486.385" y="198.939">POS</tspan></text>
<circle cx="387.5" cy="189.5" r="5.5" fill="black"/>
<circle cx="407.5" cy="189.5" r="5.5" fill="black"/>
<circle cx="427.5" cy="189.5" r="5.5" fill="black"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="44.9375" y="193.764">Tokenizer</tspan></text>
<rect x="662" y="289" width="118" height="38" fill="#64B5F6"/>
<rect x="754" y="279" width="20" height="8" fill="#64B5F6"/>
<rect x="726" y="279" width="20" height="8" fill="#64B5F6"/>
<rect x="698" y="279" width="20" height="8" fill="#64B5F6"/>
<rect x="670" y="279" width="20" height="8" fill="#64B5F6"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="689.936" y="316.939">SpaCy</tspan></text>
<rect x="662" y="249" width="118" height="38" fill="#E57373"/>
<rect x="754" y="239" width="20" height="8" fill="#E57373"/>
<rect x="726" y="239" width="20" height="8" fill="#E57373"/>
<rect x="698" y="239" width="20" height="8" fill="#E57373"/>
<rect x="670" y="239" width="20" height="8" fill="#E57373"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="700.902" y="276.939">PCA</tspan></text>
<rect x="662" y="209" width="118" height="38" fill="#4DB6AC"/>
<rect x="754" y="199" width="20" height="8" fill="#4DB6AC"/>
<rect x="726" y="199" width="20" height="8" fill="#4DB6AC"/>
<rect x="698" y="199" width="20" height="8" fill="#4DB6AC"/>
<rect x="670" y="199" width="20" height="8" fill="#4DB6AC"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="678.246" y="236.939">k-Means</tspan></text>
<rect x="662" y="169" width="118" height="38" fill="#FFD54F"/>
<rect x="754" y="159" width="20" height="8" fill="#FFD54F"/>
<rect x="726" y="159" width="20" height="8" fill="#FFD54F"/>
<rect x="698" y="159" width="20" height="8" fill="#FFD54F"/>
<rect x="670" y="159" width="20" height="8" fill="#FFD54F"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="13" font-weight="bold" letter-spacing="0em"><tspan x="668.346" y="193.161">CountVectorizer</tspan></text>
<rect x="662" y="129" width="118" height="38" fill="#90A4AE"/>
<rect x="754" y="119" width="20" height="8" fill="#90A4AE"/>
<rect x="726" y="119" width="20" height="8" fill="#90A4AE"/>
<rect x="698" y="119" width="20" height="8" fill="#90A4AE"/>
<rect x="670" y="119" width="20" height="8" fill="#90A4AE"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="676.938" y="156.939">c-TF-IDF</tspan></text>
<circle cx="387.5" cy="110.5" r="5.5" fill="black"/>
<circle cx="407.5" cy="110.5" r="5.5" fill="black"/>
<circle cx="427.5" cy="110.5" r="5.5" fill="black"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="40.8086" y="106.764">Weighting&#10;</tspan><tspan x="57.1094" y="120.764">scheme</tspan></text>
<rect x="121" y="91" width="118" height="38" fill="#90A4AE"/>
<rect x="213" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="185" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="157" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="129" y="81" width="20" height="8" fill="#90A4AE"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="135.938" y="117.939">c-TF-IDF</tspan></text>
<rect x="253" y="91" width="118" height="38" fill="#90A4AE"/>
<rect x="345" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="317" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="289" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="261" y="81" width="20" height="8" fill="#90A4AE"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="14" font-weight="bold" letter-spacing="0em"><tspan x="271.326" y="107.058">c-TF-IDF + &#10;</tspan><tspan x="292.025" y="124.058">BM25</tspan></text>
<rect x="448" y="91" width="118" height="38" fill="#90A4AE"/>
<rect x="540" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="512" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="484" y="81" width="20" height="8" fill="#90A4AE"/>
<rect x="456" y="81" width="20" height="8" fill="#90A4AE"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="14" font-weight="bold" letter-spacing="0em"><tspan x="466.326" y="107.058">c-TF-IDF + &#10;</tspan><tspan x="457.453" y="124.058">Normalization</tspan></text>
<circle cx="387.5" cy="30.5" r="5.5" fill="black"/>
<circle cx="407.5" cy="30.5" r="5.5" fill="black"/>
<circle cx="427.5" cy="30.5" r="5.5" fill="black"/>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" font-weight="bold" letter-spacing="0em"><tspan x="10.3984" y="25.7637">Representation&#10;</tspan><tspan x="61.4102" y="39.7637">Tuning</tspan></text>
<text fill="black" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="12" letter-spacing="0em"><tspan x="51.6484" y="11.7637">(optional)&#10;</tspan></text>
<rect x="121" y="11" width="118" height="38" fill="#3F51B5"/>
<rect x="213" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="185" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="157" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="129" y="1" width="20" height="8" fill="#3F51B5"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="135.732" y="37.9395">GPT / T5</tspan></text>
<rect x="253" y="11" width="118" height="38" fill="#3F51B5"/>
<rect x="345" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="317" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="289" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="261" y="1" width="20" height="8" fill="#3F51B5"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="266.932" y="37.9395">KeyBERT</tspan></text>
<rect x="448" y="11" width="118" height="38" fill="#3F51B5"/>
<rect x="540" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="512" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="484" y="1" width="20" height="8" fill="#3F51B5"/>
<rect x="456" y="1" width="20" height="8" fill="#3F51B5"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="481.863" y="37.9395">MMR</tspan></text>
<rect x="865" y="308" width="118" height="38" fill="#64B5F6"/>
<rect x="957" y="298" width="20" height="8" fill="#64B5F6"/>
<rect x="929" y="298" width="20" height="8" fill="#64B5F6"/>
<rect x="901" y="298" width="20" height="8" fill="#64B5F6"/>
<rect x="873" y="298" width="20" height="8" fill="#64B5F6"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="889.527" y="335.939">TF-IDF</tspan></text>
<rect x="865" y="268" width="118" height="38" fill="#E57373"/>
<rect x="957" y="258" width="20" height="8" fill="#E57373"/>
<rect x="929" y="258" width="20" height="8" fill="#E57373"/>
<rect x="901" y="258" width="20" height="8" fill="#E57373"/>
<rect x="873" y="258" width="20" height="8" fill="#E57373"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="15" font-weight="bold" letter-spacing="0em"><tspan x="871.306" y="293.955">TruncatedSVD</tspan></text>
<rect x="865" y="228" width="118" height="38" fill="#4DB6AC"/>
<rect x="957" y="218" width="20" height="8" fill="#4DB6AC"/>
<rect x="929" y="218" width="20" height="8" fill="#4DB6AC"/>
<rect x="901" y="218" width="20" height="8" fill="#4DB6AC"/>
<rect x="873" y="218" width="20" height="8" fill="#4DB6AC"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="890.709" y="255.939">BIRCH</tspan></text>
<rect x="865" y="188" width="118" height="38" fill="#FFD54F"/>
<rect x="957" y="178" width="20" height="8" fill="#FFD54F"/>
<rect x="929" y="178" width="20" height="8" fill="#FFD54F"/>
<rect x="901" y="178" width="20" height="8" fill="#FFD54F"/>
<rect x="873" y="178" width="20" height="8" fill="#FFD54F"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="13" font-weight="bold" letter-spacing="0em"><tspan x="871.346" y="212.161">CountVectorizer</tspan></text>
<rect x="865" y="148" width="118" height="38" fill="#90A4AE"/>
<rect x="957" y="138" width="20" height="8" fill="#90A4AE"/>
<rect x="929" y="138" width="20" height="8" fill="#90A4AE"/>
<rect x="901" y="138" width="20" height="8" fill="#90A4AE"/>
<rect x="873" y="138" width="20" height="8" fill="#90A4AE"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="15" font-weight="bold" letter-spacing="0em"><tspan x="889.756" y="163.955">c-TF-IDF &#10;</tspan><tspan x="895.264" y="181.955">+ BM25</tspan></text>
<rect x="865" y="108" width="118" height="38" fill="#3F51B5"/>
<rect x="957" y="98" width="20" height="8" fill="#3F51B5"/>
<rect x="929" y="98" width="20" height="8" fill="#3F51B5"/>
<rect x="901" y="98" width="20" height="8" fill="#3F51B5"/>
<rect x="873" y="98" width="20" height="8" fill="#3F51B5"/>
<text fill="white" xml:space="preserve" style="white-space: pre" font-family="Tahoma" font-size="20" font-weight="bold" letter-spacing="0em"><tspan x="904.854" y="133.939">GPT</tspan></text>
<path d="M642.061 231.061C642.646 230.475 642.646 229.525 642.061 228.939L632.515 219.393C631.929 218.808 630.979 218.808 630.393 219.393C629.808 219.979 629.808 220.929 630.393 221.515L638.879 230L630.393 238.485C629.808 239.071 629.808 240.021 630.393 240.607C630.979 241.192 631.929 241.192 632.515 240.607L642.061 231.061ZM579 231.5L641 231.5L641 228.5L579 228.5L579 231.5Z" fill="black"/>
<defs>
<radialGradient id="paint0_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(466.944 429.845) scale(8.01)">
<stop offset="0.5" stop-color="#FDE030"/>
<stop offset="0.919" stop-color="#F7C02B"/>
<stop offset="1" stop-color="#F4A223"/>
</radialGradient>
<linearGradient id="paint1_linear_31_1943" x1="466.944" y1="437.706" x2="466.944" y2="421.984" gradientUnits="userSpaceOnUse">
<stop offset="0.158" stop-color="#F4A223"/>
<stop offset="0.333" stop-color="#F7C02B"/>
<stop offset="0.807" stop-color="#FDE030" stop-opacity="0"/>
</linearGradient>
<radialGradient id="paint2_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(462.172 430.015) rotate(-10.6121) scale(2.49432 2.36965)">
<stop stop-color="#ED7770"/>
<stop offset="0.9" stop-color="#ED7770" stop-opacity="0"/>
</radialGradient>
<radialGradient id="paint3_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(471.628 428.247) rotate(-10.6121) scale(2.49404 2.36938)">
<stop stop-color="#ED7770"/>
<stop offset="0.9" stop-color="#ED7770" stop-opacity="0"/>
</radialGradient>
<radialGradient id="paint4_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(462.552 434.229) scale(5.41589)">
<stop offset="0.33" stop-color="#FFF176"/>
<stop offset="1" stop-color="#FFC400"/>
</radialGradient>
<radialGradient id="paint5_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(462.104 434.2) scale(5.47088 5.47084)">
<stop offset="0.33" stop-color="#FFF176"/>
<stop offset="1" stop-color="#FFC400"/>
</radialGradient>
<radialGradient id="paint6_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(471.321 434.236) rotate(180) scale(5.40773)">
<stop offset="0.33" stop-color="#FFF176"/>
<stop offset="1" stop-color="#FFC400"/>
</radialGradient>
<radialGradient id="paint7_radial_31_1943" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(471.768 434.2) rotate(180) scale(5.471 5.47084)">
<stop offset="0.33" stop-color="#FFF176"/>
<stop offset="1" stop-color="#FFC400"/>
</radialGradient>
</defs>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 32 KiB