{"id":"W1560117764","doi":"10.1007/s11390-011-9410-0","title":"A New Multiword Expression Metric and Its Applications","year":2011,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Metric (unit); Artificial intelligence; Natural language processing; Theory of computation; Question answering; Semantics (computer science); Expression (computer science); Natural language; Programming language","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":[0.000467961,0.00008372147,0.0001473085,0.001226981,0.0001443248,0.0001037329,0.001342912,0.00007697843,0.000001360182],"category_scores_gemma":[0.00008102047,0.0000607156,0.00001500462,0.002190766,0.0001709645,0.001027007,0.0006805386,0.0002169053,0.000001138433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996251,"about_ca_system_score_gemma":0.0001725744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002130631,"about_ca_topic_score_gemma":2.845486e-7,"domain_scores_codex":[0.9991013,0.00001033636,0.000216234,0.0002294203,0.0002668997,0.0001757813],"domain_scores_gemma":[0.9989374,0.00003369251,0.0002307856,0.0002248745,0.0004535434,0.0001197618],"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":[0.00000206579,0.0000229226,0.0002201616,0.000006590948,0.000002913718,0.00001682558,0.0002523273,1.351941e-7,0.01649422,0.08170906,0.0001495954,0.9011232],"study_design_scores_gemma":[0.0006529039,0.0008789237,0.00101181,0.0001651085,0.00001549255,0.002843563,0.00003255058,0.01513052,0.6486937,0.325928,0.004285294,0.0003620991],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007456586,0.005272257,0.9861393,0.0007845656,0.00009590999,0.00008089829,7.864157e-8,0.0001263526,0.00004407466],"genre_scores_gemma":[0.3923118,0.00007504741,0.6075072,0.00006695706,0.00002848622,0.000001532371,7.828733e-9,0.000001714328,0.000007264051],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9007611,"threshold_uncertainty_score":0.2495487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01551847576225597,"score_gpt":0.266887889072479,"score_spread":0.251369413310223,"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."}}