{"id":"W86816073","doi":"","title":"A distributional account of the semantics of multiword expressions","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Lexicon; Natural language processing; Artificial intelligence; Meaning (existential); Semantics (computer science); Homogeneous; Distributional semantics; Relation (database); Linguistics; Mathematics; Semantic similarity; Psychology; Philosophy; Programming language; Database","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":[0.001137725,0.0004587515,0.0005684263,0.002887919,0.001320214,0.003388224,0.001398997,0.0009855533,0.003274668],"category_scores_gemma":[0.00589394,0.0003972121,0.0008078845,0.00337315,0.00316849,0.01052407,0.001665211,0.001106843,0.0006506125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200539,"about_ca_system_score_gemma":0.0004764207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008502461,"about_ca_topic_score_gemma":0.0009363577,"domain_scores_codex":[0.9987729,0.0003979554,0.0001696107,0.0002820156,0.0002828802,0.00009449087],"domain_scores_gemma":[0.9970011,0.001334462,0.0003785082,0.0005099348,0.0006513463,0.0001246426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006032116,0.00002661983,0.002538512,0.0001470846,0.00002801249,0.0001934957,0.001485074,0.002712981,0.005968012,0.94457,0.0009932132,0.04127681],"study_design_scores_gemma":[0.00001004902,0.00002562157,0.002207072,0.00002451699,0.00001764401,0.0004595334,0.0003987151,0.02104996,0.001603912,0.9678699,0.006310157,0.00002296784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1930039,0.001559214,0.7632216,0.002586209,0.0001782261,0.00006339153,0.0007199075,0.0007185357,0.03794896],"genre_scores_gemma":[0.9367146,0.0005330874,0.05793547,0.000261936,0.0002688646,0.00008017539,0.000547374,0.000224236,0.003434205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003388224,"threshold_uncertainty_score":0.01095492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01646161670868186,"score_gpt":0.2579161318845242,"score_spread":0.2414545151758423,"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."}}