{"id":"W2018116550","doi":"10.3115/1220355.1220445","title":"A path-based transfer model for machine translation","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine translation; Dependency grammar; Dependency (UML); Parsing; Artificial intelligence; Transfer-based machine translation; Path (computing); Natural language processing; Translation (biology); Synchronous context-free grammar; Tree (set theory); Graph; Transfer (computing); Language model; Word (group theory); Set (abstract data type); Example-based machine translation; Theoretical computer science; Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001083386,0.00008235213,0.00007378888,0.00005637657,0.00005381561,0.00005727257,0.0003405344,0.00005049724,0.000002607918],"category_scores_gemma":[0.000006274288,0.00006460305,0.00005875352,0.0001307695,0.00001137723,0.0003019502,0.00000698312,0.00005822152,0.000001437633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002463574,"about_ca_system_score_gemma":0.00007132164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001915629,"about_ca_topic_score_gemma":0.00002730086,"domain_scores_codex":[0.9994345,0.000005567325,0.0001085701,0.0001992849,0.0001163665,0.0001357643],"domain_scores_gemma":[0.9997037,0.00002183687,0.0000096177,0.0001881589,0.00004348949,0.0000332203],"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":[0.00004366578,0.0001568146,0.000005709442,0.0001257288,0.000007761261,0.000004963781,0.001372008,0.01442845,0.03191326,0.6580727,0.00008487396,0.2937841],"study_design_scores_gemma":[0.0004571698,0.00003655547,6.527097e-7,0.00001222101,0.000002477281,0.000001152698,4.575083e-7,0.8013779,0.05935944,0.1386333,0.00003238431,0.00008627855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002037105,0.0005421697,0.9953814,0.002707749,0.0000206768,0.0002327548,0.000004792005,0.0007659231,0.0001407796],"genre_scores_gemma":[0.4658371,6.540467e-7,0.5335703,0.0005314829,0.000005188027,0.00002153908,0.000003318157,0.000004223039,0.00002610713],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7869494,"threshold_uncertainty_score":0.2634436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02413003566729511,"score_gpt":0.2734985460518554,"score_spread":0.2493685103845603,"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."}}