{"id":"W2011612519","doi":"10.3115/1220355.1220361","title":"Improved word alignment using a symmetric lexicon model","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Lexicon; Natural language processing; Artificial intelligence; Word (group theory); Task (project management); Speech recognition; German; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001570424,0.0001281343,0.0001156252,0.0002097567,0.00008113169,0.0001802235,0.0007284426,0.00006551299,0.000003010413],"category_scores_gemma":[0.00002818779,0.0001033338,0.00004711405,0.0006961743,0.0000198474,0.0005622306,0.0003143432,0.0001127271,0.000005413204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002160934,"about_ca_system_score_gemma":0.0001522287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001624443,"about_ca_topic_score_gemma":0.000006108707,"domain_scores_codex":[0.9990147,0.00001037011,0.0001637318,0.000331698,0.000211467,0.0002679844],"domain_scores_gemma":[0.9993798,0.00001265337,0.00006420019,0.0004159861,0.00005538492,0.00007201153],"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":[0.000004473654,0.00009866292,0.000006935371,0.00002152354,0.00001229592,0.00001850519,0.0003590011,0.002735292,0.1287216,0.7889272,0.00005929467,0.07903518],"study_design_scores_gemma":[0.0001750243,0.00002465104,0.000001094059,0.00001965241,0.000003072327,0.00001487731,0.000004487345,0.6042015,0.1873789,0.2080175,0.000009999208,0.0001492758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005898058,0.0006194483,0.9911485,0.0005306254,0.00006620363,0.0001353858,3.451004e-7,0.0008384067,0.0007629751],"genre_scores_gemma":[0.4399583,0.000002567262,0.5594729,0.0004335138,0.00001245674,0.000004110815,2.246142e-7,0.000005448293,0.0001104981],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6014662,"threshold_uncertainty_score":0.421383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02482021988831899,"score_gpt":0.2825969827975287,"score_spread":0.2577767629092097,"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."}}