{"id":"W2946378017","doi":"10.1007/978-3-030-18305-9_16","title":"Identifying Misaligned Spans in Parallel Corpora Using Change Point Detection","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; Carleton University","funders":"","keywords":"Computer science; Parallel corpora; Machine translation; Artificial intelligence; Change detection; Identification (biology); Point (geometry); Natural language processing; Translation (biology); Quality (philosophy); German; Speech recognition; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002445788,0.001413729,0.00129105,0.004946885,0.001388794,0.002559801,0.001532505,0.001789944,0.00516665],"category_scores_gemma":[0.009459597,0.000921885,0.0008538305,0.007684851,0.0007698628,0.004229848,0.002295698,0.001744181,0.006476106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005154624,"about_ca_system_score_gemma":0.0009538479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002554127,"about_ca_topic_score_gemma":0.004047349,"domain_scores_codex":[0.9966171,0.0005067562,0.0003383136,0.001470534,0.0008642337,0.0002030645],"domain_scores_gemma":[0.9921764,0.003117394,0.0008128906,0.001674499,0.002020318,0.0001985741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001339386,0.0003701081,0.01263534,0.001239795,0.0002942713,0.002098222,0.001370432,0.01070247,0.1315898,0.005211669,0.0272516,0.8058969],"study_design_scores_gemma":[0.0002593736,0.001229215,0.07444388,0.0004157145,0.0009384603,0.007219679,0.003248652,0.5257438,0.19608,0.03792515,0.1521443,0.0003517389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.30359,0.006108159,0.6395823,0.0007439799,0.001595194,0.0004599859,0.01264254,0.02253887,0.01273902],"genre_scores_gemma":[0.4693291,0.002116809,0.47177,0.0002432734,0.0006893263,0.0005210665,0.04223698,0.003247041,0.009846328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00516665,"threshold_uncertainty_score":0.01728415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04631436178743084,"score_gpt":0.2887615899639254,"score_spread":0.2424472281764946,"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."}}