{ "schema_version": 3, "complete": true, "profile": { "path": "training_profile.json", "sha256": "34f45832bdedc1b8322b26936dd88667dfecb360d941a7f54f60ae31a1fb4e10", "recipe_id": "nllb200-spm8k-directional-v3" }, "mt_standardization": { "id": "formosan-mt-standard-v3", "sha256": "4bbded87eb4833b2d1cd5a88a1f2b059560416e0e69ecfa55433a77f418c903e", "namespace": "formosan-mt" }, "model_family": "nllb", "contract": { "input_sha256": "238b96ea87716a749391d7157ce99f1611c1d4a489c4c108c315553505ca1f29", "corpus_manifest_sha256": "0179c1fa87c990f3e4b4fe9615d1a0a9265a1afbd222c7cabe2393f21eaffe25", "validation_report_sha256": "7cba1a2c4661189e63e10fb16cdbc64c271fd32be3cab19771d148d5288c1afa", "run_contract_sha256": "4cfe683caf4d25810d668f761921cb154a2d41e4e83822352faacc2d5b14293f", "checkpoint_metadata_sha256": "31bfbf36e640caeaed0f3b61e7b3d8661cf77bdece1179561a6d21bf29b52859" }, "input": "private_no_bible:chinese", "model": "FormosanBank/nllb200-formosan-zh-spm8k", "tokenizer": "FormosanBank/nllb200-formosan-zh-spm8k", "direction": "f2zh", "target_lang": "chinese", "bleu_tokenize": "zh", "lowercase_bleu": false, "split": "test", "samples": 64356, "headline_metadata_mode": "default", "global": { "samples": 64356, "BLEU": 12.580738587412997, "chrF2": 12.96470590849762, "TER": 82.85484609070636, "exact_match_rate": 0.0069457393250046615, "empty_output_rate": 0.00013984710050344958, "character_length_ratio": 0.9735837589431371, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "metadata_modes": { "default": { "samples": 64356, "BLEU": 12.580738587412997, "chrF2": 12.96470590849762, "TER": 82.85484609070636, "exact_match_rate": 0.0069457393250046615, "empty_output_rate": 0.00013984710050344958, "character_length_ratio": 0.9735837589431371, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } } }, "metadata_fallbacks": { "default": { "domain_fallback_rows": 64356, "dialect_fallback_rows": 64356 } }, "bootstrap_95_ci": { "status": "skipped", "samples": 0, "seed": 42 }, "by_language": { "ami": { "samples": 11271, "BLEU": 13.1918555311043, "chrF2": 13.378851866289018, "TER": 80.5114298774068, "exact_match_rate": 0.0030165912518853697, "empty_output_rate": 0.0, "character_length_ratio": 0.9545612209503989, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "bnn": { "samples": 6112, "BLEU": 11.10412132497452, "chrF2": 11.8546422628787, "TER": 88.67577392432739, "exact_match_rate": 0.005726439790575916, "empty_output_rate": 0.0001636125654450262, "character_length_ratio": 1.0428235373472847, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "ckv": { "samples": 3038, "BLEU": 15.171470002087373, "chrF2": 14.808325172166564, "TER": 76.72054372037238, "exact_match_rate": 0.005924950625411455, "empty_output_rate": 0.0, "character_length_ratio": 0.9807046979865772, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "dru": { "samples": 6109, "BLEU": 5.940996423160562, "chrF2": 7.037003101226312, "TER": 102.81002819723521, "exact_match_rate": 0.0022917007693566867, "empty_output_rate": 0.0004910787362907187, "character_length_ratio": 1.0361885969307136, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "pwn": { "samples": 5718, "BLEU": 8.521265940455624, "chrF2": 9.674811375535183, "TER": 93.4649114743248, "exact_match_rate": 0.0013990905911157748, "empty_output_rate": 0.0003497726477789437, "character_length_ratio": 1.0221799857015816, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "pyu": { "samples": 4280, "BLEU": 19.798357966901257, "chrF2": 18.771919267723025, "TER": 73.93693575821013, "exact_match_rate": 0.0308411214953271, "empty_output_rate": 0.0, "character_length_ratio": 0.9459577012994074, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "ssf": { "samples": 1673, "BLEU": 15.879819541690464, "chrF2": 17.03540529123015, "TER": 70.98675877950488, "exact_match_rate": 0.005977286312014346, "empty_output_rate": 0.0, "character_length_ratio": 0.9727298044172147, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "sxr": { "samples": 1781, "BLEU": 13.114989144321365, "chrF2": 13.68203020438861, "TER": 76.028900676788, "exact_match_rate": 0.005614823133071308, "empty_output_rate": 0.0, "character_length_ratio": 0.9551852007922127, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "szy": { "samples": 2055, "BLEU": 12.490528817195182, "chrF2": 14.561259511691485, "TER": 75.3939821068499, "exact_match_rate": 0.0038929440389294406, "empty_output_rate": 0.0, "character_length_ratio": 0.9021482336135377, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "tao": { "samples": 1838, "BLEU": 10.60189532011366, "chrF2": 12.097253808423574, "TER": 86.38102865278519, "exact_match_rate": 0.003808487486398259, "empty_output_rate": 0.0, "character_length_ratio": 1.0268809557673162, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "tay": { "samples": 6723, "BLEU": 10.030658272767216, "chrF2": 10.982138055853184, "TER": 78.01421413446823, "exact_match_rate": 0.007437156031533542, "empty_output_rate": 0.0, "character_length_ratio": 0.8772094926350246, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "trv": { "samples": 6983, "BLEU": 14.434006728137819, "chrF2": 15.235502409976897, "TER": 80.84272268857266, "exact_match_rate": 0.011313189173707576, "empty_output_rate": 0.00028640985249892595, "character_length_ratio": 0.960600440397052, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "tsu": { "samples": 2164, "BLEU": 11.895805977241574, "chrF2": 12.90299438484368, "TER": 80.67225218412307, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9650275854408117, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "xnb": { "samples": 2728, "BLEU": 19.39856378760136, "chrF2": 18.488341275928676, "TER": 69.2817191639682, "exact_match_rate": 0.013196480938416423, "empty_output_rate": 0.0, "character_length_ratio": 0.9773734780253946, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "xsy": { "samples": 1883, "BLEU": 11.518316944569966, "chrF2": 12.476203336723275, "TER": 77.74666348903719, "exact_match_rate": 0.003186404673393521, "empty_output_rate": 0.0005310674455655868, "character_length_ratio": 0.9228345005528935, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } } }, "by_source_bucket": { "Formosan-Academia-Sinica-Oral-Legends": { "samples": 260, "BLEU": 1.5184047323368557, "chrF2": 3.607752879476709, "TER": 147.0039364338825, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.3767271742075318, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Boyizhenu-Narrative-Oral-Literature-Tapangu": { "samples": 20, "BLEU": 0.0, "chrF2": 0.0, "TER": 114.39999999999999, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.872, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Bunun-Moriguchi-Northern-Texts": { "samples": 382, "BLEU": 4.556482074148768, "chrF2": 7.167874351913245, "TER": 96.64069264069263, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9919803600654664, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-CIP-Atayal-Grammar-Overview": { "samples": 33, "BLEU": 26.084925543784756, "chrF2": 35.72891315451452, "TER": 60.1027397260274, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0418918918918918, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Deng-Fangqing-Introduction-Puyuma-Grammar": { "samples": 376, "BLEU": 24.499437200984158, "chrF2": 28.174278345762676, "TER": 58.88787602552416, "exact_match_rate": 0.06914893617021277, "empty_output_rate": 0.0, "character_length_ratio": 0.9226395939086295, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Glosbe": { "samples": 2186, "BLEU": 14.93117749734157, "chrF2": 14.478334396414597, "TER": 73.35618631458007, "exact_match_rate": 0.0009149130832570906, "empty_output_rate": 0.0, "character_length_ratio": 0.913203808685123, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Hala-Saku-La-Videos": { "samples": 47, "BLEU": 5.061816442197886, "chrF2": 8.42442769014718, "TER": 83.09919114516816, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.6130952380952381, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Huang-Huijuan-Shi-Chaokai-Introduction-Bunun-Grammar": { "samples": 716, "BLEU": 12.189672284506477, "chrF2": 13.740446665721755, "TER": 76.70538348082596, "exact_match_rate": 0.013966480446927373, "empty_output_rate": 0.0, "character_length_ratio": 0.7565281655444244, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-ILRDF-42-Language-Practice-Word-Lists": { "samples": 3, "BLEU": 3.8815952835694683, "chrF2": 3.424641860039361, "TER": 88.88888888888889, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.6296296296296297, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-ILRDF-Tousvusvutu-Kita": { "samples": 497, "BLEU": 5.152060142903115, "chrF2": 6.809234748570317, "TER": 104.84475110892065, "exact_match_rate": 0.004024144869215292, "empty_output_rate": 0.0, "character_length_ratio": 1.004917888820585, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Indigenous-Education-Resource-Center-Keelung-City-Serangawan-No": { "samples": 23, "BLEU": 28.15899781413618, "chrF2": 23.667599175837104, "TER": 53.50877192982456, "exact_match_rate": 0.043478260869565216, "empty_output_rate": 0.0, "character_length_ratio": 0.9094827586206896, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Indigenous-Language-Literary-Awards": { "samples": 821, "BLEU": 2.412181696193584, "chrF2": 4.5279484158761845, "TER": 100.01695274422546, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.934447142092918, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Kucapungane": { "samples": 12, "BLEU": 2.892986805656571, "chrF2": 5.051336155822737, "TER": 103.76175548589342, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9752144899904671, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Kumu-Tapas-Tribal-Memory-Oral-History-Wushe-Incident-II": { "samples": 71, "BLEU": 2.9635392138545416, "chrF2": 6.484189254367516, "TER": 88.0565138820437, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.6026764377887526, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Li-Peirong-Xu-Weisheng-Introduction-Truku-Grammar": { "samples": 468, "BLEU": 22.879843447542882, "chrF2": 24.303648070257005, "TER": 60.86889539362193, "exact_match_rate": 0.042735042735042736, "empty_output_rate": 0.0, "character_length_ratio": 0.8839035333707235, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-PaiwanStories": { "samples": 13, "BLEU": 3.320115399578185, "chrF2": 7.1048822760617, "TER": 89.1891891891892, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.8608247422680413, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Puyuma-Katipol-Kopfjagdriten": { "samples": 38, "BLEU": 3.015861276037805, "chrF2": 4.76287474070312, "TER": 92.85714285714286, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.7934782608695652, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-SEALS": { "samples": 47, "BLEU": 4.759285283577419, "chrF2": 5.930459034869349, "TER": 111.32756132756131, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.1212903225806452, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Shen-Wenqi-Introduction-Sakizaya-Grammar": { "samples": 67, "BLEU": 16.992614089854257, "chrF2": 17.75684375216057, "TER": 65.62889165628891, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9242979242979243, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Sing-Olam-Hong-Tinglan-Aboriginal-Education-World-Issue": { "samples": 1, "BLEU": 71.65313105737896, "chrF2": 68.86227544910179, "TER": 25.0, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.75, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Song-Limei-Introduction-Seediq-Grammar": { "samples": 442, "BLEU": 19.971996882565136, "chrF2": 23.122087305085547, "TER": 64.06685236768801, "exact_match_rate": 0.05203619909502263, "empty_output_rate": 0.0, "character_length_ratio": 0.8887895050685748, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Wu-Jinglan-Introduction-Amis-Grammar": { "samples": 288, "BLEU": 23.971418217708198, "chrF2": 26.20025205918842, "TER": 56.87943262411348, "exact_match_rate": 0.04861111111111111, "empty_output_rate": 0.0, "character_length_ratio": 0.8612731422774537, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Xie-Fuhui-Introduction-Kavalan-Grammar": { "samples": 33, "BLEU": 27.56170123220992, "chrF2": 34.8621449696623, "TER": 63.52395672333848, "exact_match_rate": 0.06060606060606061, "empty_output_rate": 0.0, "character_length_ratio": 1.011378002528445, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Zhao-Shanhe-Li-Taiyuan-Zhu-Qingyi-Aboriginal-Education-World-Issue-16": { "samples": 5, "BLEU": 78.9773161836023, "chrF2": 76.09937642638272, "TER": 14.634146341463413, "exact_match_rate": 0.4, "empty_output_rate": 0.0, "character_length_ratio": 1.0, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-Zheng-ACL-2024": { "samples": 11928, "BLEU": 15.780769976983771, "chrF2": 16.42245978564808, "TER": 70.74925721061533, "exact_match_rate": 0.009054325955734407, "empty_output_rate": 0.0, "character_length_ratio": 0.9224855323138599, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-ePark": { "samples": 5700, "BLEU": 38.26167160586107, "chrF2": 32.28225904343755, "TER": 42.84845553175316, "exact_match_rate": 0.028771929824561403, "empty_output_rate": 0.0, "character_length_ratio": 0.9634230597287887, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Formosan-gitbook_translations": { "samples": 51, "BLEU": 3.2141866387955265, "chrF2": 8.521924203356665, "TER": 122.24409448818898, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.1219110378912684, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "culture": { "samples": 5489, "BLEU": 6.480767384550856, "chrF2": 7.660942069794658, "TER": 97.1531089786563, "exact_match_rate": 0.00018218254691200583, "empty_output_rate": 0.00018218254691200583, "character_length_ratio": 0.9973183587863729, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "essays": { "samples": 3722, "BLEU": 16.328664532508153, "chrF2": 15.989650491484719, "TER": 71.99628228108611, "exact_match_rate": 0.008060182697474477, "empty_output_rate": 0.0, "character_length_ratio": 1.013505336474708, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "ntu": { "samples": 440, "BLEU": 17.345798902609253, "chrF2": 15.844215543415258, "TER": 76.1023690126232, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9769941225860621, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "picture_book": { "samples": 12634, "BLEU": 12.23364317472049, "chrF2": 13.761258091926761, "TER": 78.72619308231174, "exact_match_rate": 0.002691150862751306, "empty_output_rate": 7.915149596327371e-05, "character_length_ratio": 0.9670261525343629, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "picture_story": { "samples": 863, "BLEU": 9.080114094143601, "chrF2": 9.65627900464358, "TER": 90.16095665775266, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9506388767429432, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "presidential_apology": { "samples": 108, "BLEU": 4.400830341996858, "chrF2": 6.4000097247865275, "TER": 113.2823488045007, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.1276301892923877, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "reading_writing": { "samples": 1124, "BLEU": 9.71120279354296, "chrF2": 9.901041025507332, "TER": 87.93712212817412, "exact_match_rate": 0.0008896797153024911, "empty_output_rate": 0.0, "character_length_ratio": 0.981299672744273, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "youtube": { "samples": 15448, "BLEU": 6.083847184995035, "chrF2": 7.481384089171102, "TER": 101.0536648581735, "exact_match_rate": 0.0004531330916623511, "empty_output_rate": 0.0004531330916623511, "character_length_ratio": 1.0220858782839062, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } } }, "by_dialect": { "Central": { "samples": 1462, "BLEU": 6.245837215434144, "chrF2": 7.437307813519742, "TER": 102.61820687279304, "exact_match_rate": 0.002051983584131327, "empty_output_rate": 0.0006839945280437756, "character_length_ratio": 1.0643430520317765, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Coastal": { "samples": 4090, "BLEU": 12.62785293823784, "chrF2": 13.352495811232142, "TER": 82.80232427576915, "exact_match_rate": 0.001466992665036675, "empty_output_rate": 0.0, "character_length_ratio": 0.9847345307281669, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Dawu": { "samples": 960, "BLEU": 6.636383121958551, "chrF2": 7.847467315350563, "TER": 104.00590644946175, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0849292635218124, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "DeluValley": { "samples": 439, "BLEU": 7.162521403162108, "chrF2": 8.501476537286635, "TER": 93.18593946157065, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9764104580302733, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Dona": { "samples": 363, "BLEU": 10.053733462553387, "chrF2": 9.974232937576398, "TER": 91.17067402443831, "exact_match_rate": 0.008264462809917356, "empty_output_rate": 0.0, "character_length_ratio": 1.0028869084975525, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Duda": { "samples": 677, "BLEU": 8.54491075080391, "chrF2": 9.038500417850894, "TER": 90.9516517173485, "exact_match_rate": 0.005908419497784343, "empty_output_rate": 0.0, "character_length_ratio": 0.8946756375114212, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Eastern": { "samples": 2631, "BLEU": 6.740811782877297, "chrF2": 7.895764731761029, "TER": 97.69556854469738, "exact_match_rate": 0.0011402508551881414, "empty_output_rate": 0.0, "character_length_ratio": 0.9951046317714778, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "FourSeasons": { "samples": 76, "BLEU": 4.424597259237414, "chrF2": 6.383118262768753, "TER": 105.2596089008766, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0513530135301352, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Hengchun": { "samples": 234, "BLEU": 15.791912276224933, "chrF2": 15.31039939820434, "TER": 75.69772434521254, "exact_match_rate": 0.008547008547008548, "empty_output_rate": 0.0, "character_length_ratio": 1.0211640211640212, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Jianhe": { "samples": 286, "BLEU": 25.567508607352632, "chrF2": 22.7006312699475, "TER": 61.663239661868865, "exact_match_rate": 0.04195804195804196, "empty_output_rate": 0.0, "character_length_ratio": 0.9455693446549096, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Junqun": { "samples": 2663, "BLEU": 10.662204649619605, "chrF2": 11.780536944704087, "TER": 88.93881419594904, "exact_match_rate": 0.004506196019526849, "empty_output_rate": 0.0003755163349605708, "character_length_ratio": 1.0220821214435436, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Kanakanavu": { "samples": 2728, "BLEU": 19.39856378760136, "chrF2": 18.488341275928676, "TER": 69.2817191639682, "exact_match_rate": 0.013196480938416423, "empty_output_rate": 0.0, "character_length_ratio": 0.9773734780253946, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Kaqun": { "samples": 172, "BLEU": 16.774848869485286, "chrF2": 15.542877633403249, "TER": 68.89018351296242, "exact_match_rate": 0.01744186046511628, "empty_output_rate": 0.0, "character_length_ratio": 0.9372159090909091, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Kavalan": { "samples": 3038, "BLEU": 15.171470002087373, "chrF2": 14.808325172166564, "TER": 76.72054372037238, "exact_match_rate": 0.005924950625411455, "empty_output_rate": 0.0, "character_length_ratio": 0.9807046979865772, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Luanqun": { "samples": 155, "BLEU": 17.349484372027945, "chrF2": 17.598349739237214, "TER": 71.81554337310546, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.1005674653215636, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Malan": { "samples": 1230, "BLEU": 10.221167917101575, "chrF2": 10.439882337669687, "TER": 82.39746523499385, "exact_match_rate": 0.0008130081300813008, "empty_output_rate": 0.0, "character_length_ratio": 0.8698444895199459, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Maolin": { "samples": 410, "BLEU": 4.273942963093996, "chrF2": 5.276588781857147, "TER": 100.75223319228961, "exact_match_rate": 0.0024390243902439024, "empty_output_rate": 0.004878048780487805, "character_length_ratio": 0.9729977116704805, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Nanwang": { "samples": 1892, "BLEU": 14.57954039098228, "chrF2": 14.258816665992901, "TER": 85.16901657719309, "exact_match_rate": 0.022198731501057084, "empty_output_rate": 0.0, "character_length_ratio": 0.9574596552859809, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Northern": { "samples": 2159, "BLEU": 9.938683098210683, "chrF2": 11.156971342176261, "TER": 88.06784142789266, "exact_match_rate": 0.0013895321908290875, "empty_output_rate": 0.0004631773969430292, "character_length_ratio": 1.0169857104340794, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Saaroa": { "samples": 1781, "BLEU": 13.114989144321365, "chrF2": 13.68203020438861, "TER": 76.028900676788, "exact_match_rate": 0.005614823133071308, "empty_output_rate": 0.0, "character_length_ratio": 0.9551852007922127, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Saisiyat": { "samples": 1877, "BLEU": 11.461679154597425, "chrF2": 12.441476730582655, "TER": 77.79412349409566, "exact_match_rate": 0.002131060202450719, "empty_output_rate": 0.0005327650506126798, "character_length_ratio": 0.9228555617044826, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Sakizaya": { "samples": 2055, "BLEU": 12.490528817195182, "chrF2": 14.561259511691485, "TER": 75.3939821068499, "exact_match_rate": 0.0038929440389294406, "empty_output_rate": 0.0, "character_length_ratio": 0.9021482336135377, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Sekolik": { "samples": 430, "BLEU": 2.813092140199989, "chrF2": 5.591458672900994, "TER": 93.83398407788651, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.8395688321732405, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Southern": { "samples": 780, "BLEU": 15.796482686409094, "chrF2": 14.845783907869976, "TER": 75.59048898017221, "exact_match_rate": 0.005128205128205128, "empty_output_rate": 0.0, "character_length_ratio": 0.9534954639018068, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Tanqun": { "samples": 184, "BLEU": 16.428580485687892, "chrF2": 16.320602885354223, "TER": 71.26141552511416, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0512963479230555, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Tegudaya": { "samples": 1502, "BLEU": 18.866407115218493, "chrF2": 18.089019543909796, "TER": 71.87598972446071, "exact_match_rate": 0.02796271637816245, "empty_output_rate": 0.0, "character_length_ratio": 0.9561662198391421, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Thao": { "samples": 1673, "BLEU": 15.879819541690464, "chrF2": 17.03540529123015, "TER": 70.98675877950488, "exact_match_rate": 0.005977286312014346, "empty_output_rate": 0.0, "character_length_ratio": 0.9727298044172147, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Truku": { "samples": 3204, "BLEU": 17.498129570998714, "chrF2": 18.218042405574568, "TER": 76.84859333997844, "exact_match_rate": 0.009987515605493134, "empty_output_rate": 0.0006242197253433209, "character_length_ratio": 1.016496910372456, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Tsou": { "samples": 2164, "BLEU": 11.895805977241574, "chrF2": 12.90299438484368, "TER": 80.67225218412307, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.9650275854408117, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Wanda": { "samples": 40, "BLEU": 9.759361343346518, "chrF2": 12.427580196511215, "TER": 84.28005284015853, "exact_match_rate": 0.025, "empty_output_rate": 0.0, "character_length_ratio": 0.9300613496932515, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Wanshan": { "samples": 912, "BLEU": 4.783936442989583, "chrF2": 6.165013325791203, "TER": 99.1668616896794, "exact_match_rate": 0.0010964912280701754, "empty_output_rate": 0.0, "character_length_ratio": 0.9984970624402241, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Wenshui": { "samples": 35, "BLEU": 12.232564716539688, "chrF2": 12.825466615679723, "TER": 79.42122186495176, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0926517571884984, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Wutai": { "samples": 2231, "BLEU": 5.560392839668127, "chrF2": 6.605242162459571, "TER": 105.53900221560089, "exact_match_rate": 0.002689376961004034, "empty_output_rate": 0.00044822949350067237, "character_length_ratio": 1.0327670191279554, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Xiqun": { "samples": 634, "BLEU": 38.94182683168665, "chrF2": 32.7957607713137, "TER": 42.73384947328341, "exact_match_rate": 0.055205047318611984, "empty_output_rate": 0.0, "character_length_ratio": 0.9568452380952381, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Xiuguluan": { "samples": 2210, "BLEU": 11.03007805840091, "chrF2": 12.433794737348038, "TER": 89.38989352712522, "exact_match_rate": 0.007239819004524887, "empty_output_rate": 0.0, "character_length_ratio": 0.9983890327879209, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Yami": { "samples": 1838, "BLEU": 10.60189532011366, "chrF2": 12.097253808423574, "TER": 86.38102865278519, "exact_match_rate": 0.003808487486398259, "empty_output_rate": 0.0, "character_length_ratio": 1.0268809557673162, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "YilanZeaol": { "samples": 390, "BLEU": 2.9104309307826854, "chrF2": 4.647373218475065, "TER": 94.05347264904734, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 0.7690119760479042, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Zeaol": { "samples": 308, "BLEU": 3.7135631295484477, "chrF2": 5.443722731848967, "TER": 104.93009565857247, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0196219191194065, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Zhiben": { "samples": 834, "BLEU": 32.380374722084525, "chrF2": 30.384844655711102, "TER": 49.310409975439256, "exact_match_rate": 0.050359712230215826, "empty_output_rate": 0.0, "character_length_ratio": 0.9372444444444444, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "Zhuoqun": { "samples": 703, "BLEU": 10.560107321229836, "chrF2": 10.98310054202614, "TER": 91.74892256360351, "exact_match_rate": 0.001422475106685633, "empty_output_rate": 0.0, "character_length_ratio": 1.0717540637965042, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "unknown": { "samples": 12906, "BLEU": 12.861387188089601, "chrF2": 13.547981744471688, "TER": 78.81499768554235, "exact_match_rate": 0.006121183945451728, "empty_output_rate": 0.0, "character_length_ratio": 0.9422104966725459, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } } }, "by_length_bin": { "004_008": { "samples": 29612, "BLEU": 15.800227037482845, "chrF2": 15.308497380504566, "TER": 76.3719293314718, "exact_match_rate": 0.01472376063757936, "empty_output_rate": 0.00027016074564365796, "character_length_ratio": 0.9294510528432304, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "009_016": { "samples": 23105, "BLEU": 13.472340011569313, "chrF2": 13.660536137778026, "TER": 82.01923448653837, "exact_match_rate": 0.0004760874269638606, "empty_output_rate": 0.0, "character_length_ratio": 0.9809750373923358, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "017_032": { "samples": 9642, "BLEU": 10.597229992386678, "chrF2": 11.753171184438896, "TER": 85.23120014906445, "exact_match_rate": 0.0, "empty_output_rate": 0.00010371292263015972, "character_length_ratio": 0.9915622408160732, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } }, "033_plus": { "samples": 1997, "BLEU": 7.3139233977674705, "chrF2": 9.211145132235528, "TER": 95.05836715635215, "exact_match_rate": 0.0, "empty_output_rate": 0.0, "character_length_ratio": 1.0091243551633586, "signatures": { "BLEU": "nrefs:1|case:mixed|eff:yes|tok:zh|smooth:exp|version:2.5.1", "chrF2": "nrefs:1|case:mixed|eff:yes|nc:6|nw:0|space:no|version:2.5.1", "TER": "nrefs:1|case:mixed|tok:tercom|norm:yes|punct:yes|asian:yes|version:2.5.1" } } } }