{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002456224,0.0007449691,0.0007226532,0.00282732,0.0008347637,0.001822397,0.0008609626,0.001127594,0.001325929],"category_scores_gemma":[0.02045633,0.0004179091,0.0006259092,0.001913542,0.0008864859,0.00481249,0.002667968,0.001033842,0.001017556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003802336,"about_ca_system_score_gemma":0.0005957267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004823039,"about_ca_topic_score_gemma":0.0008385936,"domain_scores_codex":[0.9962781,0.001206149,0.0005335329,0.0009544573,0.00087545,0.0001523398],"domain_scores_gemma":[0.9863704,0.008462582,0.001514085,0.001483108,0.001833315,0.0003364497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009589975,0.000299506,0.05271865,0.001413574,0.0003929724,0.0006661928,0.002299741,0.01237922,0.2991968,0.01681725,0.001576804,0.6112803],"study_design_scores_gemma":[0.0000940984,0.0012326,0.1083319,0.0002342626,0.000490425,0.003693757,0.003380146,0.5285692,0.2497405,0.07728264,0.02670508,0.0002453724],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4840883,0.001593634,0.5077538,0.0002474152,0.0001570883,0.0001796649,0.0005141906,0.001157413,0.004308596],"genre_scores_gemma":[0.8126592,0.0005931136,0.1826106,0.00008799208,0.00009338513,0.0001696692,0.001826623,0.0003244131,0.001634966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00282732,"threshold_uncertainty_score":0.01298988,"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."}}