CoolFace
Apppublic

vedant2905/CrossLingual

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes
cluster_alignments_fast_align.json622 linesDownload Raw Back to layer3
1{2  "99": {3    "aligned_clusters": [4      321,5      354,6      3,7      446,8      165,9      134,10      326,11      454,12      179,13      350,14      19115    ],16    "metrics": {17      "match_percentage": 0.75,18      "source_cluster_size": 4,19      "target_cluster_sizes": [20        7,21        5,22        6,23        7,24        7,25        4,26        6,27        6,28        9,29        7,30        831      ],32      "aligned_word_count": 3,33      "total_words": 4,34      "size_threshold": 0.4,35      "translation_threshold": 0.5,36      "calign_score": 1.0,37      "colap_score": 0.938974677988871738    }39  },40  "108": {41    "aligned_clusters": [42      216,43      16544    ],45    "metrics": {46      "match_percentage": 0.6666666666666666,47      "source_cluster_size": 3,48      "target_cluster_sizes": [49        6,50        651      ],52      "aligned_word_count": 2,53      "total_words": 3,54      "size_threshold": 0.4,55      "translation_threshold": 0.5,56      "calign_score": 0.6666666666666666,57      "colap_score": 0.937616319279344958    }59  },60  "128": {61    "aligned_clusters": [62      24463    ],64    "metrics": {65      "match_percentage": 1.0,66      "source_cluster_size": 2,67      "target_cluster_sizes": [68        469      ],70      "aligned_word_count": 2,71      "total_words": 2,72      "size_threshold": 0.4,73      "translation_threshold": 0.5,74      "calign_score": 1.0,75      "colap_score": 1.076    }77  },78  "168": {79    "aligned_clusters": [80      4681    ],82    "metrics": {83      "match_percentage": 1.0,84      "source_cluster_size": 2,85      "target_cluster_sizes": [86        387      ],88      "aligned_word_count": 2,89      "total_words": 2,90      "size_threshold": 0.4,91      "translation_threshold": 0.5,92      "calign_score": 1.0,93      "colap_score": 1.094    }95  },96  "181": {97    "aligned_clusters": [98      386,99      3,100      134,101      18,102      34,103      165,104      170,105      179,106      181,107      315,108      446,109      319,110      191,111      321,112      326,113      204,114      216,115      346,116      350,117      367118    ],119    "metrics": {120      "match_percentage": 0.6666666666666666,121      "source_cluster_size": 3,122      "target_cluster_sizes": [123        7,124        4,125        3,126        5,127        6,128        7,129        7,130        6,131        7,132        6,133        6,134        4,135        5,136        4,137        6,138        5,139        6,140        5,141        4,142        7143      ],144      "aligned_word_count": 2,145      "total_words": 3,146      "size_threshold": 0.4,147      "translation_threshold": 0.5,148      "calign_score": 0.6666666666666666,149      "colap_score": 0.9209519805079316150    }151  },152  "253": {153    "aligned_clusters": [154      164,155      165,156      326,157      169,158      460,159      77,160      244,161      309,162      437,163      474,164      477,165      319166    ],167    "metrics": {168      "match_percentage": 0.6666666666666666,169      "source_cluster_size": 3,170      "target_cluster_sizes": [171        5,172        5,173        6,174        6,175        4,176        3,177        5,178        6,179        4,180        7,181        5,182        6183      ],184      "aligned_word_count": 2,185      "total_words": 3,186      "size_threshold": 0.4,187      "translation_threshold": 0.5,188      "calign_score": 0.6666666666666666,189      "colap_score": 1.0190    }191  },192  "268": {193    "aligned_clusters": [194      216195    ],196    "metrics": {197      "match_percentage": 0.6666666666666666,198      "source_cluster_size": 3,199      "target_cluster_sizes": [200        6201      ],202      "aligned_word_count": 2,203      "total_words": 3,204      "size_threshold": 0.4,205      "translation_threshold": 0.5,206      "calign_score": 0.6666666666666666,207      "colap_score": 0.9376215346835991208    }209  },210  "311": {211    "aligned_clusters": [212      450,213      42,214      118215    ],216    "metrics": {217      "match_percentage": 0.75,218      "source_cluster_size": 4,219      "target_cluster_sizes": [220        5,221        8,222        3223      ],224      "aligned_word_count": 3,225      "total_words": 4,226      "size_threshold": 0.4,227      "translation_threshold": 0.5,228      "calign_score": 0.75,229      "colap_score": 1.0230    }231  },232  "349": {233    "aligned_clusters": [234      385,235      386,236      3,237      4,238      134,239      395,240      397,241      17,242      18,243      32,244      34,245      164,246      165,247      295,248      42,249      170,250      173,251      179,252      181,253      309,254      311,255      441,256      315,257      444,258      446,259      191,260      319,261      321,262      450,263      69,264      326,265      74,266      204,267      77,268      78,269      216,270      346,271      474,272      222,273      350,274      231,275      361,276      106,277      490,278      109,279      367,280      114,281      119282    ],283    "metrics": {284      "match_percentage": 1.0,285      "source_cluster_size": 3,286      "target_cluster_sizes": [287        7,288        7,289        3,290        4,291        7,292        3,293        5,294        2,295        7,296        5,297        5,298        6,299        6,300        6,301        7,302        5,303        5,304        6,305        7,306        7,307        7,308        6,309        7,310        6,311        6,312        7,313        4,314        3,315        3,316        7,317        4,318        5,319        4,320        6,321        5,322        6,323        6,324        5,325        3,326        4,327        6,328        3,329        5,330        4,331        7,332        3,333        5,334        6335      ],336      "aligned_word_count": 3,337      "total_words": 3,338      "size_threshold": 0.4,339      "translation_threshold": 0.5,340      "calign_score": 1.0,341      "colap_score": 0.9440433315043043342    }343  },344  "377": {345    "aligned_clusters": [346      265,347      10,348      145,349      148,350      152,351      416,352      34,353      291,354      425,355      170,356      427,357      428,358      429,359      179,360      181,361      438,362      441,363      316,364      446,365      191,366      192,367      194,368      74,369      461,370      464,371      466,372      472,373      93,374      106,375      235,376      254377    ],378    "metrics": {379      "match_percentage": 0.75,380      "source_cluster_size": 4,381      "target_cluster_sizes": [382        9,383        3,384        7,385        7,386        6,387        9,388        8,389        9,390        7,391        7,392        6,393        7,394        8,395        5,396        6,397        5,398        7,399        9,400        5,401        4,402        5,403        8,404        6,405        5,406        6,407        5,408        7,409        7,410        7,411        7,412        7413      ],414      "aligned_word_count": 3,415      "total_words": 4,416      "size_threshold": 0.4,417      "translation_threshold": 0.5,418      "calign_score": 0.75,419      "colap_score": 0.8180553766414405420    }421  },422  "389": {423    "aligned_clusters": [424      321,425      385,426      231,427      17,428      309,429      444430    ],431    "metrics": {432      "match_percentage": 1.0,433      "source_cluster_size": 2,434      "target_cluster_sizes": [435        3,436        4,437        3,438        4,439        3,440        4441      ],442      "aligned_word_count": 2,443      "total_words": 2,444      "size_threshold": 0.4,445      "translation_threshold": 0.5,446      "calign_score": 1.0,447      "colap_score": 1.0448    }449  },450  "398": {451    "aligned_clusters": [452      161,453      344,454      453,455      295,456      425,457      273,458      435,459      443,460      216,461      379,462      254,463      287464    ],465    "metrics": {466      "match_percentage": 0.6666666666666666,467      "source_cluster_size": 3,468      "target_cluster_sizes": [469        5,470        6,471        5,472        5,473        7,474        3,475        5,476        5,477        5,478        3,479        5,480        4481      ],482      "aligned_word_count": 2,483      "total_words": 3,484      "size_threshold": 0.4,485      "translation_threshold": 0.5,486      "calign_score": 0.6666666666666666,487      "colap_score": 0.8389198920534715488    }489  },490  "404": {491    "aligned_clusters": [492      321,493      450,494      69,495      295,496      397497    ],498    "metrics": {499      "match_percentage": 1.0,500      "source_cluster_size": 2,501      "target_cluster_sizes": [502        2,503        3,504        4,505        3,506        3507      ],508      "aligned_word_count": 2,509      "total_words": 2,510      "size_threshold": 0.4,511      "translation_threshold": 0.5,512      "calign_score": 1.0,513      "colap_score": 1.0514    }515  },516  "415": {517    "aligned_clusters": [518      450,519      42520    ],521    "metrics": {522      "match_percentage": 0.6666666666666666,523      "source_cluster_size": 3,524      "target_cluster_sizes": [525        5,526        3527      ],528      "aligned_word_count": 2,529      "total_words": 3,530      "size_threshold": 0.4,531      "translation_threshold": 0.5,532      "calign_score": 0.6666666666666666,533      "colap_score": 1.0534    }535  },536  "431": {537    "aligned_clusters": [538      165,539      326,540      319541    ],542    "metrics": {543      "match_percentage": 0.75,544      "source_cluster_size": 4,545      "target_cluster_sizes": [546        6,547        5,548        6549      ],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": 0.9431559683843002556    }557  },558  "458": {559    "aligned_clusters": [560      385,561      3,562      134,563      17,564      32,565      164,566      165,567      173,568      179,569      309,570      444,571      446,572      191,573      321,574      326,575      77,576      78,577      474,578      350,579      222,580      231,581      490,582      109,583      114584    ],585    "metrics": {586      "match_percentage": 0.6666666666666666,587      "source_cluster_size": 3,588      "target_cluster_sizes": [589        7,590        3,591        7,592        5,593        5,594        6,595        6,596        5,597        5,598        6,599        7,600        7,601        7,602        7,603        4,604        3,605        4,606        6,607        6,608        3,609        4,610        7,611        5,612        6613      ],614      "aligned_word_count": 2,615      "total_words": 3,616      "size_threshold": 0.4,617      "translation_threshold": 0.5,618      "calign_score": 0.6666666666666666,619      "colap_score": 0.9592311397043423620    }621  }622}