{"id":"W1815301076","doi":"","title":"Measuring the Non-compositionality of Multiword Expressions","year":2010,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Principle of compositionality; Computer science; Artificial intelligence; Natural language processing; Semantics (computer science); Metric (unit); Natural language; Question answering; Combinatory categorial grammar; Distributional semantics; Expression (computer science); Information extraction; Programming language; Semantic similarity; Link grammar; Rule-based machine translation","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":[0.0003206877,0.0001290691,0.0001241634,0.0001018255,0.0001611642,0.0001252538,0.001342535,0.00005654995,0.00007263871],"category_scores_gemma":[0.0009448598,0.0001037039,0.00007467823,0.0001059037,0.000103228,0.00006612753,0.000233745,0.0003736258,0.00002953439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002584872,"about_ca_system_score_gemma":0.0002047187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003293107,"about_ca_topic_score_gemma":0.00001136313,"domain_scores_codex":[0.9983724,0.00004056933,0.0003828049,0.0002940874,0.00077271,0.0001374341],"domain_scores_gemma":[0.9972063,0.0005251223,0.0002059305,0.0003664096,0.001630294,0.00006588496],"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":[0.000007971683,0.00008515404,0.0004035165,0.000004152112,0.0000222628,0.000003137634,0.0001825618,0.03065422,0.002020244,0.9647896,0.00008612073,0.001741044],"study_design_scores_gemma":[0.0002198029,0.00001872232,0.005855537,0.00004824222,0.000003731573,0.000006160389,0.00001513646,0.8534986,0.001056702,0.1373483,0.001810826,0.0001181811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0268742,0.000003671472,0.92831,0.002429605,0.003925258,0.0001463843,0.00004269719,0.00006808791,0.03820004],"genre_scores_gemma":[0.8587013,0.00000124731,0.1404796,0.0002488654,0.0004621551,0.00001084235,0.0000216225,0.000005778777,0.00006852356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8318272,"threshold_uncertainty_score":0.4228924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0730969691908334,"score_gpt":0.3251466138805431,"score_spread":0.2520496446897096,"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."}}