{"id":"W2114580886","doi":"10.1007/s10844-010-0130-7","title":"A vector-space dynamic feature for phrase-based statistical machine translation","year":2010,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Infocomm Research; McGill University","keywords":"Computer science; Phrase; Machine translation; Feature vector; Artificial intelligence; Feature (linguistics); Translation (biology); Natural language processing; Context (archaeology); Feature selection; Support vector machine; Function (biology); Decoding methods; Vector space; Vector space model; Feature engineering; Algorithm; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007198855,0.0005418954,0.0009047428,0.001609654,0.0005962663,0.000912906,0.0008456854,0.0008281308,0.006909385],"category_scores_gemma":[0.002125017,0.0002201401,0.0007424739,0.002846689,0.0003003929,0.001406975,0.001111824,0.0008527219,0.00332702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003806266,"about_ca_system_score_gemma":0.0009388211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002853685,"about_ca_topic_score_gemma":0.00309319,"domain_scores_codex":[0.9993368,0.0001722219,0.00007553618,0.0001586994,0.00018084,0.00007586437],"domain_scores_gemma":[0.9992107,0.0002712563,0.00006905888,0.0001480445,0.0002644408,0.00003637939],"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":[0.0007078913,0.0001546119,0.0007779434,0.0001570102,0.00006816407,0.0001763935,0.0000502956,0.009700661,0.04437185,0.008430603,0.01059492,0.9248098],"study_design_scores_gemma":[0.0001248621,0.0005330485,0.003721004,0.00004209085,0.0001137893,0.0006242741,0.00009851355,0.9139028,0.04093364,0.01766381,0.02214398,0.00009807409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02715882,0.0008017231,0.9613603,0.0002436874,0.0002766343,0.0001215853,0.002106223,0.005954913,0.001976215],"genre_scores_gemma":[0.3872654,0.0006689263,0.5963452,0.0001768952,0.0002865927,0.0004382579,0.008728821,0.0006517966,0.005438205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006909385,"threshold_uncertainty_score":0.02311414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01104179445258608,"score_gpt":0.2851133414040508,"score_spread":0.2740715469514647,"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."}}