{"id":"W2077255111","doi":"10.3115/1118627.1118636","title":"Acquiring collocations for lexical choice between near-synonyms","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Pennsylvania","keywords":"Collocation (remote sensing); Computer science; Synonym (taxonomy); Natural language processing; Artificial intelligence; Lexical density; Word (group theory); Linguistics; Task (project management); Lexical item","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00012284,0.000088963,0.0001066739,0.00004508928,0.000229257,0.0002889925,0.0007840122,0.00006737423,0.00004290736],"category_scores_gemma":[0.0001450572,0.00007587661,0.00004739703,0.0003210517,0.00004328089,0.0004734139,0.0001582979,0.00008724941,0.00003929213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003419212,"about_ca_system_score_gemma":0.00001807135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000254698,"about_ca_topic_score_gemma":0.000006978635,"domain_scores_codex":[0.9992124,0.00001377327,0.0001469561,0.0002601459,0.0001408236,0.000225847],"domain_scores_gemma":[0.9992313,0.000230273,0.00004008496,0.0003419999,0.00008486577,0.00007143775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002110035,0.00013738,0.00449679,0.00008264928,0.00004164983,0.000004740985,0.001016195,0.000011719,0.002998661,0.3622804,0.06321792,0.5657098],"study_design_scores_gemma":[0.001400346,0.0004834425,0.003709274,0.0001581773,0.00005577656,0.00003476641,0.0000315232,0.4769807,0.1442367,0.1512024,0.2200715,0.001635429],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001483237,0.0004656219,0.9909392,0.003679454,0.00006809281,0.0002047956,0.000001922692,0.000974679,0.002182987],"genre_scores_gemma":[0.3991996,0.000001374566,0.5985628,0.0003659344,0.00008893998,0.00003475111,0.000001385144,0.000005845578,0.001739304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5640743,"threshold_uncertainty_score":0.3094158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04991608310263382,"score_gpt":0.3119821999308962,"score_spread":0.2620661168282623,"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."}}