vedant2905/CrossLingual
0
1{2 "11": {3 "aligned_clusters": [4 196,5 292,6 293,7 478,8 201,9 363,10 428,11 237,12 207,13 406,14 475,15 89,16 283,17 317,18 62,19 25520 ],21 "metrics": {22 "match_percentage": 0.6666666666666666,23 "source_cluster_size": 3,24 "target_cluster_sizes": [25 5,26 7,27 5,28 7,29 6,30 6,31 5,32 5,33 5,34 7,35 4,36 5,37 7,38 6,39 6,40 341 ],42 "aligned_word_count": 2,43 "total_words": 3,44 "size_threshold": 0.4,45 "translation_threshold": 0.5,46 "calign_score": 0.6666666666666666,47 "colap_score": 0.957429086264026348 }49 },50 "18": {51 "aligned_clusters": [52 26,53 333,54 141,55 9556 ],57 "metrics": {58 "match_percentage": 0.75,59 "source_cluster_size": 4,60 "target_cluster_sizes": [61 5,62 5,63 7,64 965 ],66 "aligned_word_count": 3,67 "total_words": 4,68 "size_threshold": 0.4,69 "translation_threshold": 0.5,70 "calign_score": 0.75,71 "colap_score": 1.072 }73 },74 "19": {75 "aligned_clusters": [76 229,77 69,78 21,79 438,80 41381 ],82 "metrics": {83 "match_percentage": 0.8333333333333334,84 "source_cluster_size": 6,85 "target_cluster_sizes": [86 12,87 7,88 9,89 8,90 1391 ],92 "aligned_word_count": 5,93 "total_words": 6,94 "size_threshold": 0.4,95 "translation_threshold": 0.5,96 "calign_score": 0.8333333333333334,97 "colap_score": 0.964050931234443598 }99 },100 "21": {101 "aligned_clusters": [102 162,103 196,104 40,105 428,106 270,107 18,108 154,109 283,110 62111 ],112 "metrics": {113 "match_percentage": 0.6666666666666666,114 "source_cluster_size": 3,115 "target_cluster_sizes": [116 7,117 4,118 5,119 3,120 6,121 5,122 4,123 5,124 6125 ],126 "aligned_word_count": 2,127 "total_words": 3,128 "size_threshold": 0.4,129 "translation_threshold": 0.5,130 "calign_score": 0.6666666666666666,131 "colap_score": 0.9196107693460218132 }133 },134 "46": {135 "aligned_clusters": [136 5,137 229,138 170,139 141,140 466,141 23,142 27,143 413144 ],145 "metrics": {146 "match_percentage": 0.75,147 "source_cluster_size": 4,148 "target_cluster_sizes": [149 8,150 6,151 9,152 7,153 9,154 9,155 8,156 9157 ],158 "aligned_word_count": 3,159 "total_words": 4,160 "size_threshold": 0.4,161 "translation_threshold": 0.5,162 "calign_score": 0.75,163 "colap_score": 0.96936515119966164 }165 },166 "66": {167 "aligned_clusters": [168 354,169 396,170 461,171 492,172 87,173 57174 ],175 "metrics": {176 "match_percentage": 0.6666666666666666,177 "source_cluster_size": 3,178 "target_cluster_sizes": [179 6,180 7,181 7,182 5,183 3,184 7185 ],186 "aligned_word_count": 2,187 "total_words": 3,188 "size_threshold": 0.4,189 "translation_threshold": 0.5,190 "calign_score": 0.6666666666666666,191 "colap_score": 1.0192 }193 },194 "109": {195 "aligned_clusters": [196 400,197 468,198 349,199 359200 ],201 "metrics": {202 "match_percentage": 1.0,203 "source_cluster_size": 2,204 "target_cluster_sizes": [205 4,206 4,207 4,208 4209 ],210 "aligned_word_count": 2,211 "total_words": 2,212 "size_threshold": 0.4,213 "translation_threshold": 0.5,214 "calign_score": 1.0,215 "colap_score": 1.0216 }217 },218 "112": {219 "aligned_clusters": [220 323,221 292,222 393,223 51,224 122,225 191226 ],227 "metrics": {228 "match_percentage": 0.6666666666666666,229 "source_cluster_size": 3,230 "target_cluster_sizes": [231 6,232 7,233 7,234 5,235 6,236 6237 ],238 "aligned_word_count": 2,239 "total_words": 3,240 "size_threshold": 0.4,241 "translation_threshold": 0.5,242 "calign_score": 0.6666666666666666,243 "colap_score": 0.9364254045136475244 }245 },246 "117": {247 "aligned_clusters": [248 312,249 27,250 141,251 413252 ],253 "metrics": {254 "match_percentage": 0.75,255 "source_cluster_size": 4,256 "target_cluster_sizes": [257 9,258 7,259 5,260 8261 ],262 "aligned_word_count": 3,263 "total_words": 4,264 "size_threshold": 0.4,265 "translation_threshold": 0.5,266 "calign_score": 0.75,267 "colap_score": 0.9411327851456015268 }269 },270 "121": {271 "aligned_clusters": [272 329,273 138,274 77,275 49,276 146,277 115278 ],279 "metrics": {280 "match_percentage": 1.0,281 "source_cluster_size": 2,282 "target_cluster_sizes": [283 3,284 2,285 3,286 4,287 3,288 4289 ],290 "aligned_word_count": 2,291 "total_words": 2,292 "size_threshold": 0.4,293 "translation_threshold": 0.5,294 "calign_score": 1.0,295 "colap_score": 1.0296 }297 },298 "127": {299 "aligned_clusters": [300 393,301 18,302 422,303 22304 ],305 "metrics": {306 "match_percentage": 0.6666666666666666,307 "source_cluster_size": 3,308 "target_cluster_sizes": [309 7,310 5,311 6,312 7313 ],314 "aligned_word_count": 2,315 "total_words": 3,316 "size_threshold": 0.4,317 "translation_threshold": 0.5,318 "calign_score": 0.6666666666666666,319 "colap_score": 0.9576630358174226320 }321 },322 "132": {323 "aligned_clusters": [324 102,325 317,326 78,327 146328 ],329 "metrics": {330 "match_percentage": 1.0,331 "source_cluster_size": 2,332 "target_cluster_sizes": [333 3,334 4,335 3,336 4337 ],338 "aligned_word_count": 2,339 "total_words": 2,340 "size_threshold": 0.4,341 "translation_threshold": 0.5,342 "calign_score": 1.0,343 "colap_score": 1.0344 }345 },346 "137": {347 "aligned_clusters": [348 226,349 482,350 293,351 393,352 141,353 336,354 81,355 467,356 312,357 26,358 475,359 95360 ],361 "metrics": {362 "match_percentage": 0.6666666666666666,363 "source_cluster_size": 3,364 "target_cluster_sizes": [365 5,366 6,367 5,368 7,369 2,370 7,371 5,372 3,373 6,374 6,375 6,376 4377 ],378 "aligned_word_count": 2,379 "total_words": 3,380 "size_threshold": 0.4,381 "translation_threshold": 0.5,382 "calign_score": 0.6666666666666666,383 "colap_score": 1.0384 }385 },386 "162": {387 "aligned_clusters": [388 262,389 359,390 141,391 400,392 464,393 468,394 373,395 214,396 26,397 349,398 95399 ],400 "metrics": {401 "match_percentage": 0.6666666666666666,402 "source_cluster_size": 3,403 "target_cluster_sizes": [404 5,405 5,406 7,407 6,408 6,409 4,410 4,411 7,412 4,413 7,414 4415 ],416 "aligned_word_count": 2,417 "total_words": 3,418 "size_threshold": 0.4,419 "translation_threshold": 0.5,420 "calign_score": 0.6666666666666666,421 "colap_score": 0.9395025860163402422 }423 },424 "173": {425 "aligned_clusters": [426 69,427 326,428 455,429 141,430 335,431 339,432 53,433 26,434 95435 ],436 "metrics": {437 "match_percentage": 0.6666666666666666,438 "source_cluster_size": 3,439 "target_cluster_sizes": [440 5,441 5,442 7,443 5,444 7,445 4,446 4,447 2,448 3449 ],450 "aligned_word_count": 2,451 "total_words": 3,452 "size_threshold": 0.4,453 "translation_threshold": 0.5,454 "calign_score": 0.6666666666666666,455 "colap_score": 1.0456 }457 },458 "174": {459 "aligned_clusters": [460 283,461 229462 ],463 "metrics": {464 "match_percentage": 0.75,465 "source_cluster_size": 4,466 "target_cluster_sizes": [467 9,468 5469 ],470 "aligned_word_count": 3,471 "total_words": 4,472 "size_threshold": 0.4,473 "translation_threshold": 0.5,474 "calign_score": 0.75,475 "colap_score": 0.9214886072319306476 }477 },478 "188": {479 "aligned_clusters": [480 441481 ],482 "metrics": {483 "match_percentage": 0.6666666666666666,484 "source_cluster_size": 3,485 "target_cluster_sizes": [486 5487 ],488 "aligned_word_count": 2,489 "total_words": 3,490 "size_threshold": 0.4,491 "translation_threshold": 0.5,492 "calign_score": 1.0,493 "colap_score": 0.9235628770455672494 }495 },496 "198": {497 "aligned_clusters": [498 293,499 329,500 138,501 459,502 77,503 462,504 49,505 18,506 115,507 146,508 181,509 475,510 187511 ],512 "metrics": {513 "match_percentage": 0.6666666666666666,514 "source_cluster_size": 3,515 "target_cluster_sizes": [516 7,517 3,518 2,519 3,520 4,521 3,522 7,523 7,524 7,525 4,526 6,527 6,528 6529 ],530 "aligned_word_count": 2,531 "total_words": 3,532 "size_threshold": 0.4,533 "translation_threshold": 0.5,534 "calign_score": 0.6666666666666666,535 "colap_score": 1.0536 }537 },538 "200": {539 "aligned_clusters": [540 354,541 87542 ],543 "metrics": {544 "match_percentage": 0.75,545 "source_cluster_size": 4,546 "target_cluster_sizes": [547 7,548 7549 ],550 "aligned_word_count": 3,551 "total_words": 4,552 "size_threshold": 0.4,553 "translation_threshold": 0.5,554 "calign_score": 0.75,555 "colap_score": 0.9336072039352747556 }557 },558 "201": {559 "aligned_clusters": [560 374561 ],562 "metrics": {563 "match_percentage": 0.6666666666666666,564 "source_cluster_size": 3,565 "target_cluster_sizes": [566 4567 ],568 "aligned_word_count": 2,569 "total_words": 3,570 "size_threshold": 0.4,571 "translation_threshold": 0.5,572 "calign_score": 0.6666666666666666,573 "colap_score": 1.0574 }575 },576 "227": {577 "aligned_clusters": [578 26,579 333,580 141,581 95582 ],583 "metrics": {584 "match_percentage": 0.75,585 "source_cluster_size": 4,586 "target_cluster_sizes": [587 5,588 5,589 7,590 9591 ],592 "aligned_word_count": 3,593 "total_words": 4,594 "size_threshold": 0.4,595 "translation_threshold": 0.5,596 "calign_score": 0.75,597 "colap_score": 1.0598 }599 },600 "228": {601 "aligned_clusters": [602 323,603 292,604 393,605 51,606 122,607 191608 ],609 "metrics": {610 "match_percentage": 0.6666666666666666,611 "source_cluster_size": 3,612 "target_cluster_sizes": [613 6,614 7,615 7,616 5,617 6,618 6619 ],620 "aligned_word_count": 2,621 "total_words": 3,622 "size_threshold": 0.4,623 "translation_threshold": 0.5,624 "calign_score": 0.6666666666666666,625 "colap_score": 1.0626 }627 },628 "245": {629 "aligned_clusters": [630 461,631 165,632 445633 ],634 "metrics": {635 "match_percentage": 1.0,636 "source_cluster_size": 2,637 "target_cluster_sizes": [638 4,639 4,640 3641 ],642 "aligned_word_count": 2,643 "total_words": 2,644 "size_threshold": 0.4,645 "translation_threshold": 0.5,646 "calign_score": 1.0,647 "colap_score": 1.0648 }649 },650 "263": {651 "aligned_clusters": [652 336,653 226,654 482655 ],656 "metrics": {657 "match_percentage": 1.0,658 "source_cluster_size": 2,659 "target_cluster_sizes": [660 2,661 3,662 4663 ],664 "aligned_word_count": 2,665 "total_words": 2,666 "size_threshold": 0.4,667 "translation_threshold": 0.5,668 "calign_score": 1.0,669 "colap_score": 1.0670 }671 },672 "266": {673 "aligned_clusters": [674 229675 ],676 "metrics": {677 "match_percentage": 0.75,678 "source_cluster_size": 4,679 "target_cluster_sizes": [680 9681 ],682 "aligned_word_count": 3,683 "total_words": 4,684 "size_threshold": 0.4,685 "translation_threshold": 0.5,686 "calign_score": 0.75,687 "colap_score": 0.9695753817308066688 }689 },690 "278": {691 "aligned_clusters": [692 329,693 138,694 77,695 49,696 146,697 115698 ],699 "metrics": {700 "match_percentage": 1.0,701 "source_cluster_size": 2,702 "target_cluster_sizes": [703 3,704 2,705 3,706 4,707 3,708 4709 ],710 "aligned_word_count": 2,711 "total_words": 2,712 "size_threshold": 0.4,713 "translation_threshold": 0.5,714 "calign_score": 1.0,715 "colap_score": 1.0716 }717 },718 "292": {719 "aligned_clusters": [720 26,721 333,722 141,723 95724 ],725 "metrics": {726 "match_percentage": 0.75,727 "source_cluster_size": 4,728 "target_cluster_sizes": [729 5,730 5,731 7,732 9733 ],734 "aligned_word_count": 3,735 "total_words": 4,736 "size_threshold": 0.4,737 "translation_threshold": 0.5,738 "calign_score": 0.75,739 "colap_score": 1.0740 }741 },742 "315": {743 "aligned_clusters": [744 372,745 262746 ],747 "metrics": {748 "match_percentage": 0.6666666666666666,749 "source_cluster_size": 3,750 "target_cluster_sizes": [751 6,752 3753 ],754 "aligned_word_count": 2,755 "total_words": 3,756 "size_threshold": 0.4,757 "translation_threshold": 0.5,758 "calign_score": 0.6666666666666666,759 "colap_score": 0.9601375628294461760 }761 },762 "325": {763 "aligned_clusters": [764 293,765 329,766 138,767 459,768 77,769 462,770 49,771 18,772 115,773 146,774 181,775 475,776 187777 ],778 "metrics": {779 "match_percentage": 0.6666666666666666,780 "source_cluster_size": 3,781 "target_cluster_sizes": [782 7,783 3,784 2,785 3,786 4,787 3,788 7,789 7,790 7,791 4,792 6,793 6,794 6795 ],796 "aligned_word_count": 2,797 "total_words": 3,798 "size_threshold": 0.4,799 "translation_threshold": 0.5,800 "calign_score": 0.6666666666666666,801 "colap_score": 1.0802 }803 },804 "377": {805 "aligned_clusters": [806 196,807 69,808 393,809 428,810 62,811 122,812 380,813 158814 ],815 "metrics": {816 "match_percentage": 0.6666666666666666,817 "source_cluster_size": 3,818 "target_cluster_sizes": [819 5,820 7,821 7,822 4,823 5,824 6,825 6,826 6827 ],828 "aligned_word_count": 2,829 "total_words": 3,830 "size_threshold": 0.4,831 "translation_threshold": 0.5,832 "calign_score": 0.6666666666666666,833 "colap_score": 1.0834 }835 },836 "383": {837 "aligned_clusters": [838 36,839 141,840 146,841 312,842 475843 ],844 "metrics": {845 "match_percentage": 0.6666666666666666,846 "source_cluster_size": 3,847 "target_cluster_sizes": [848 5,849 7,850 3,851 5,852 6853 ],854 "aligned_word_count": 2,855 "total_words": 3,856 "size_threshold": 0.4,857 "translation_threshold": 0.5,858 "calign_score": 0.6666666666666666,859 "colap_score": 1.0860 }861 },862 "397": {863 "aligned_clusters": [864 239865 ],866 "metrics": {867 "match_percentage": 0.6666666666666666,868 "source_cluster_size": 3,869 "target_cluster_sizes": [870 3871 ],872 "aligned_word_count": 2,873 "total_words": 3,874 "size_threshold": 0.4,875 "translation_threshold": 0.5,876 "calign_score": 0.6666666666666666,877 "colap_score": 1.0878 }879 },880 "415": {881 "aligned_clusters": [882 386,883 211,884 438,885 219,886 413887 ],888 "metrics": {889 "match_percentage": 0.6666666666666666,890 "source_cluster_size": 6,891 "target_cluster_sizes": [892 14,893 9,894 10,895 8,896 13897 ],898 "aligned_word_count": 4,899 "total_words": 6,900 "size_threshold": 0.4,901 "translation_threshold": 0.5,902 "calign_score": 0.6666666666666666,903 "colap_score": 0.9346758074652051904 }905 },906 "445": {907 "aligned_clusters": [908 27909 ],910 "metrics": {911 "match_percentage": 0.6666666666666666,912 "source_cluster_size": 6,913 "target_cluster_sizes": [914 9915 ],916 "aligned_word_count": 4,917 "total_words": 6,918 "size_threshold": 0.4,919 "translation_threshold": 0.5,920 "calign_score": 0.6666666666666666,921 "colap_score": 0.9999999999999999922 }923 },924 "460": {925 "aligned_clusters": [926 336,927 226,928 482929 ],930 "metrics": {931 "match_percentage": 1.0,932 "source_cluster_size": 2,933 "target_cluster_sizes": [934 2,935 3,936 4937 ],938 "aligned_word_count": 2,939 "total_words": 2,940 "size_threshold": 0.4,941 "translation_threshold": 0.5,942 "calign_score": 1.0,943 "colap_score": 1.0944 }945 },946 "485": {947 "aligned_clusters": [948 262,949 359,950 141,951 400,952 464,953 468,954 373,955 214,956 26,957 349,958 95959 ],960 "metrics": {961 "match_percentage": 0.6666666666666666,962 "source_cluster_size": 3,963 "target_cluster_sizes": [964 5,965 5,966 7,967 6,968 6,969 4,970 4,971 7,972 4,973 7,974 4975 ],976 "aligned_word_count": 2,977 "total_words": 3,978 "size_threshold": 0.4,979 "translation_threshold": 0.5,980 "calign_score": 0.6666666666666666,981 "colap_score": 0.9999999999999998982 }983 },984 "491": {985 "aligned_clusters": [986 380987 ],988 "metrics": {989 "match_percentage": 0.75,990 "source_cluster_size": 4,991 "target_cluster_sizes": [992 6993 ],994 "aligned_word_count": 3,995 "total_words": 4,996 "size_threshold": 0.4,997 "translation_threshold": 0.5,998 "calign_score": 0.75,999 "colap_score": 0.94181914294610781000 }1001 },1002 "493": {1003 "aligned_clusters": [1004 461,1005 165,1006 4451007 ],1008 "metrics": {1009 "match_percentage": 1.0,1010 "source_cluster_size": 2,1011 "target_cluster_sizes": [1012 4,1013 4,1014 31015 ],1016 "aligned_word_count": 2,1017 "total_words": 2,1018 "size_threshold": 0.4,1019 "translation_threshold": 0.5,1020 "calign_score": 1.0,1021 "colap_score": 1.01022 }1023 },1024 "498": {1025 "aligned_clusters": [1026 138,1027 141,1028 18,1029 146,1030 406,1031 36,1032 293,1033 49,1034 181,1035 312,1036 187,1037 317,1038 329,1039 459,1040 77,1041 78,1042 207,1043 462,1044 475,1045 102,1046 363,1047 1151048 ],1049 "metrics": {1050 "match_percentage": 0.6666666666666666,1051 "source_cluster_size": 3,1052 "target_cluster_sizes": [1053 7,1054 5,1055 3,1056 2,1057 3,1058 4,1059 3,1060 4,1061 7,1062 3,1063 7,1064 7,1065 6,1066 7,1067 5,1068 4,1069 4,1070 5,1071 7,1072 6,1073 6,1074 61075 ],1076 "aligned_word_count": 2,1077 "total_words": 3,1078 "size_threshold": 0.4,1079 "translation_threshold": 0.5,1080 "calign_score": 0.6666666666666666,1081 "colap_score": 0.9592112103498641082 }1083 }1084}