{"id":"W2962696263","doi":"","title":"Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation","year":2018,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Machine translation; Sentence; Artificial intelligence; Task (project management); Natural language processing; Translation (biology); Feature engineering; Recurrent neural network; Parallel corpora; Baseline (sea); Artificial neural network; Feature (linguistics); Feature extraction; Speech recognition; Deep learning","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":[0.001058967,0.001651277,0.001080006,0.001273979,0.0006713939,0.0008562485,0.0009095888,0.0008769784,0.003375013],"category_scores_gemma":[0.004423319,0.0005207679,0.001009605,0.001644602,0.0003777567,0.002301431,0.001061894,0.00128753,0.003191439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004087793,"about_ca_system_score_gemma":0.001091588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002475366,"about_ca_topic_score_gemma":0.006049282,"domain_scores_codex":[0.9992028,0.000250522,0.0000871623,0.0001994176,0.00018923,0.00007087732],"domain_scores_gemma":[0.998403,0.0005940583,0.0001621127,0.0002409803,0.0005570083,0.00004281625],"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":[0.0005703729,0.000479305,0.002073808,0.0007271477,0.0003263101,0.001100267,0.0005443455,0.06104802,0.1405773,0.007311102,0.01963778,0.7656043],"study_design_scores_gemma":[0.00007344663,0.0003390429,0.001361759,0.00004061663,0.0002555379,0.0003632751,0.0001688803,0.9005783,0.07185357,0.01399085,0.01091485,0.00005992521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09780084,0.001507756,0.8837446,0.0005762064,0.0004348702,0.0002187674,0.0009230502,0.009709714,0.005084129],"genre_scores_gemma":[0.3819616,0.0008031826,0.6018493,0.0004756417,0.0003404006,0.0003577566,0.006096927,0.0009261385,0.007189017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003375013,"threshold_uncertainty_score":0.01129055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03912998338648059,"score_gpt":0.3326886547462771,"score_spread":0.2935586713597965,"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."}}