CoolFace
Apppublic

vedant2905/CrossLingual

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes
cluster_alignments_fast_align.json524 linesDownload Raw Back to layer10
1{2  "11": {3    "aligned_clusters": [4      130,5      395,6      270,7      18,8      406,9      26,10      283,11      157,12      292,13      293,14      167,15      428,16      433,17      51,18      181,19      187,20      317,21      62,22      196,23      324,24      326,25      327,26      201,27      207,28      81,29      89,30      475,31      478,32      482,33      483,34      363,35      237,36      366,37      113,38      126,39      25540    ],41    "metrics": {42      "match_percentage": 0.6666666666666666,43      "source_cluster_size": 3,44      "target_cluster_sizes": [45        7,46        5,47        6,48        5,49        6,50        7,51        4,52        3,53        5,54        4,55        5,56        7,57        7,58        5,59        7,60        6,61        6,62        5,63        4,64        5,65        5,66        7,67        4,68        3,69        4,70        6,71        5,72        4,73        5,74        7,75        6,76        5,77        6,78        3,79        4,80        381      ],82      "aligned_word_count": 2,83      "total_words": 3,84      "size_threshold": 0.4,85      "translation_threshold": 0.5,86      "calign_score": 0.6666666666666666,87      "colap_score": 0.940705075408950188    }89  },90  "21": {91    "aligned_clusters": [92      28393    ],94    "metrics": {95      "match_percentage": 0.6666666666666666,96      "source_cluster_size": 3,97      "target_cluster_sizes": [98        599      ],100      "aligned_word_count": 2,101      "total_words": 3,102      "size_threshold": 0.4,103      "translation_threshold": 0.5,104      "calign_score": 0.6666666666666666,105      "colap_score": 0.9228803395187927106    }107  },108  "46": {109    "aligned_clusters": [110      27,111      413112    ],113    "metrics": {114      "match_percentage": 0.75,115      "source_cluster_size": 4,116      "target_cluster_sizes": [117        9,118        8119      ],120      "aligned_word_count": 3,121      "total_words": 4,122      "size_threshold": 0.4,123      "translation_threshold": 0.5,124      "calign_score": 0.75,125      "colap_score": 0.9411580458943916126    }127  },128  "117": {129    "aligned_clusters": [130      312,131      27,132      141,133      413134    ],135    "metrics": {136      "match_percentage": 0.75,137      "source_cluster_size": 4,138      "target_cluster_sizes": [139        9,140        7,141        5,142        8143      ],144      "aligned_word_count": 3,145      "total_words": 4,146      "size_threshold": 0.4,147      "translation_threshold": 0.5,148      "calign_score": 0.75,149      "colap_score": 0.9493249815349946150    }151  },152  "121": {153    "aligned_clusters": [154      329,155      138,156      77,157      49,158      146,159      115160    ],161    "metrics": {162      "match_percentage": 1.0,163      "source_cluster_size": 2,164      "target_cluster_sizes": [165        3,166        2,167        3,168        4,169        3,170        4171      ],172      "aligned_word_count": 2,173      "total_words": 2,174      "size_threshold": 0.4,175      "translation_threshold": 0.5,176      "calign_score": 1.0,177      "colap_score": 0.9354566403241911178    }179  },180  "132": {181    "aligned_clusters": [182      102,183      317,184      78,185      146186    ],187    "metrics": {188      "match_percentage": 1.0,189      "source_cluster_size": 2,190      "target_cluster_sizes": [191        3,192        4,193        3,194        4195      ],196      "aligned_word_count": 2,197      "total_words": 2,198      "size_threshold": 0.4,199      "translation_threshold": 0.5,200      "calign_score": 1.0,201      "colap_score": 1.0202    }203  },204  "137": {205    "aligned_clusters": [206      226,207      482,208      293,209      393,210      141,211      336,212      81,213      467,214      312,215      26,216      475,217      95218    ],219    "metrics": {220      "match_percentage": 0.6666666666666666,221      "source_cluster_size": 3,222      "target_cluster_sizes": [223        5,224        6,225        5,226        7,227        2,228        7,229        5,230        3,231        6,232        6,233        6,234        4235      ],236      "aligned_word_count": 2,237      "total_words": 3,238      "size_threshold": 0.4,239      "translation_threshold": 0.5,240      "calign_score": 0.6666666666666666,241      "colap_score": 0.9614278033079239242    }243  },244  "174": {245    "aligned_clusters": [246      283,247      229248    ],249    "metrics": {250      "match_percentage": 0.75,251      "source_cluster_size": 4,252      "target_cluster_sizes": [253        9,254        5255      ],256      "aligned_word_count": 3,257      "total_words": 4,258      "size_threshold": 0.4,259      "translation_threshold": 0.5,260      "calign_score": 0.75,261      "colap_score": 0.9217761912708258262    }263  },264  "198": {265    "aligned_clusters": [266      293,267      329,268      138,269      459,270      77,271      462,272      49,273      18,274      115,275      146,276      181,277      475,278      187279    ],280    "metrics": {281      "match_percentage": 0.6666666666666666,282      "source_cluster_size": 3,283      "target_cluster_sizes": [284        7,285        3,286        2,287        3,288        4,289        3,290        7,291        7,292        7,293        4,294        6,295        6,296        6297      ],298      "aligned_word_count": 2,299      "total_words": 3,300      "size_threshold": 0.4,301      "translation_threshold": 0.5,302      "calign_score": 0.6666666666666666,303      "colap_score": 0.8982147297044544304    }305  },306  "263": {307    "aligned_clusters": [308      336,309      226,310      482311    ],312    "metrics": {313      "match_percentage": 1.0,314      "source_cluster_size": 2,315      "target_cluster_sizes": [316        2,317        3,318        4319      ],320      "aligned_word_count": 2,321      "total_words": 2,322      "size_threshold": 0.4,323      "translation_threshold": 0.5,324      "calign_score": 1.0,325      "colap_score": 1.0326    }327  },328  "278": {329    "aligned_clusters": [330      329,331      138,332      77,333      49,334      146,335      115336    ],337    "metrics": {338      "match_percentage": 1.0,339      "source_cluster_size": 2,340      "target_cluster_sizes": [341        3,342        2,343        3,344        4,345        3,346        4347      ],348      "aligned_word_count": 2,349      "total_words": 2,350      "size_threshold": 0.4,351      "translation_threshold": 0.5,352      "calign_score": 1.0,353      "colap_score": 0.9354566403241911354    }355  },356  "325": {357    "aligned_clusters": [358      293,359      329,360      138,361      459,362      77,363      462,364      49,365      18,366      115,367      146,368      181,369      475,370      187371    ],372    "metrics": {373      "match_percentage": 0.6666666666666666,374      "source_cluster_size": 3,375      "target_cluster_sizes": [376        7,377        3,378        2,379        3,380        4,381        3,382        7,383        7,384        7,385        4,386        6,387        6,388        6389      ],390      "aligned_word_count": 2,391      "total_words": 3,392      "size_threshold": 0.4,393      "translation_threshold": 0.5,394      "calign_score": 0.6666666666666666,395      "colap_score": 0.8982147297044543396    }397  },398  "383": {399    "aligned_clusters": [400      36,401      141,402      146,403      312,404      475405    ],406    "metrics": {407      "match_percentage": 0.6666666666666666,408      "source_cluster_size": 3,409      "target_cluster_sizes": [410        5,411        7,412        3,413        5,414        6415      ],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": 1.0422    }423  },424  "445": {425    "aligned_clusters": [426      27427    ],428    "metrics": {429      "match_percentage": 0.6666666666666666,430      "source_cluster_size": 6,431      "target_cluster_sizes": [432        9433      ],434      "aligned_word_count": 4,435      "total_words": 6,436      "size_threshold": 0.4,437      "translation_threshold": 0.5,438      "calign_score": 0.6666666666666666,439      "colap_score": 0.9361331297250138440    }441  },442  "460": {443    "aligned_clusters": [444      336,445      226,446      482447    ],448    "metrics": {449      "match_percentage": 1.0,450      "source_cluster_size": 2,451      "target_cluster_sizes": [452        2,453        3,454        4455      ],456      "aligned_word_count": 2,457      "total_words": 2,458      "size_threshold": 0.4,459      "translation_threshold": 0.5,460      "calign_score": 1.0,461      "colap_score": 1.0462    }463  },464  "498": {465    "aligned_clusters": [466      138,467      141,468      18,469      146,470      406,471      36,472      293,473      49,474      181,475      312,476      187,477      317,478      329,479      459,480      77,481      78,482      207,483      462,484      475,485      102,486      363,487      115488    ],489    "metrics": {490      "match_percentage": 0.6666666666666666,491      "source_cluster_size": 3,492      "target_cluster_sizes": [493        7,494        5,495        3,496        2,497        3,498        4,499        3,500        4,501        7,502        3,503        7,504        7,505        6,506        7,507        5,508        4,509        4,510        5,511        7,512        6,513        6,514        6515      ],516      "aligned_word_count": 2,517      "total_words": 3,518      "size_threshold": 0.4,519      "translation_threshold": 0.5,520      "calign_score": 0.6666666666666666,521      "colap_score": 0.8982147297044543522    }523  }524}