{"id":"W4402672028","doi":"10.18653/v1/2024.acl-long.553","title":"BinaryAlign: Word Alignment as Binary Sequence Labeling","year":2024,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Word (group theory); Sequence (biology); Binary number; Natural language processing; Sequence labeling; Artificial intelligence; Pseudorandom binary sequence; Arithmetic; Linguistics; Mathematics; Biology; Genetics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003978574,0.0001690043,0.0001304441,0.0002382788,0.00009808349,0.0004860513,0.0007241925,0.00007470736,0.0004044962],"category_scores_gemma":[0.00002105979,0.000145409,0.00008130259,0.0007180582,0.00004348034,0.0007956916,0.0003544872,0.0001537592,0.002208858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009945234,"about_ca_system_score_gemma":0.0001220874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006183804,"about_ca_topic_score_gemma":0.000001840804,"domain_scores_codex":[0.9984755,0.00005803915,0.0002477066,0.0005527169,0.0003513059,0.0003147618],"domain_scores_gemma":[0.9992154,0.0001025291,0.00002536644,0.0004744388,0.0000618063,0.0001204549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003218687,0.00008863959,0.00002881349,0.00009159739,0.00004570369,0.001116419,0.0006697691,0.000008002728,0.06111693,0.3421784,0.03535047,0.559302],"study_design_scores_gemma":[0.000240678,0.0006358066,0.0000421851,0.0008601606,0.00002411004,0.0005010232,0.0001430364,0.07961886,0.5116987,0.224713,0.1804099,0.001112608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01890235,0.001716273,0.8805131,0.01103359,0.001160288,0.0005089623,0.00000626757,0.008669853,0.07748927],"genre_scores_gemma":[0.77337,0.0002812077,0.2149366,0.002160655,0.0001087817,0.0001082271,0.000006748914,0.00002646671,0.009001313],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7544676,"threshold_uncertainty_score":0.9985681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03158959059957141,"score_gpt":0.3023630520417447,"score_spread":0.2707734614421733,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}