{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002301932,0.0002321006,0.0001560882,0.0002395998,0.0002245732,0.0004003874,0.0007900103,0.00006957733,0.0000501892],"category_scores_gemma":[0.0004445942,0.0002006908,0.00004822792,0.0003123464,0.00009119329,0.0001790027,0.0001079659,0.0003182833,0.00002417382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009703132,"about_ca_system_score_gemma":0.0001271206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003921289,"about_ca_topic_score_gemma":0.00004225256,"domain_scores_codex":[0.9980262,0.00005363364,0.000353448,0.0005504942,0.0007680751,0.0002481303],"domain_scores_gemma":[0.9971488,0.00028182,0.0002166579,0.0001864229,0.002041954,0.0001243855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003277824,0.0002129607,0.0006983272,0.00001242013,0.0000843692,0.0000421418,0.0004535936,0.05417498,0.0001478134,0.7279155,0.0004939099,0.2154361],"study_design_scores_gemma":[0.0002570271,0.0004099375,0.0002683891,0.00008841777,0.000006258335,0.00002460424,0.00001183315,0.9714423,0.0001477154,0.02583914,0.001246048,0.0002583478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007078235,0.00006588156,0.9895089,0.002222103,0.002488259,0.000209101,0.00002856237,0.0003485367,0.004420802],"genre_scores_gemma":[0.5793703,0.000002614429,0.4191837,0.0004972018,0.0008184182,0.00001592926,0.00005044606,0.000009473332,0.00005188713],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9172673,"threshold_uncertainty_score":0.8183933,"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."}}