{"id":"W2077818552","doi":"10.1162/coli.2010.36.1.36104","title":"Automatically Identifying the Source Words of Lexical Blends in English","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"University of Toronto","keywords":"Computer science; Natural language processing; Lexicon; Artificial intelligence; Task (project management); Set (abstract data type); Identification (biology); Word (group theory); Source text; Linguistics; Programming language","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":[0.0004871141,0.00009649496,0.0001304719,0.0001121288,0.00007790355,0.0001250218,0.0009260712,0.00007504258,0.000006998923],"category_scores_gemma":[0.005311776,0.00007530644,0.00004188326,0.0003932303,0.0001307066,0.0000561041,0.0002744924,0.000449149,0.000003536475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001662935,"about_ca_system_score_gemma":0.0001621159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009337953,"about_ca_topic_score_gemma":0.00001174583,"domain_scores_codex":[0.9988918,0.00004107706,0.0003363555,0.000194976,0.0003742205,0.0001615161],"domain_scores_gemma":[0.9982745,0.0007060957,0.0001239706,0.0002684813,0.0005848497,0.00004207216],"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":[0.000002720471,0.00004837625,0.0005829973,0.00003959086,0.000005846637,0.00001026458,0.001987469,0.001799811,0.0001514519,0.9835658,0.0003029417,0.0115027],"study_design_scores_gemma":[0.0001260753,0.00001869201,0.001018703,0.00006443867,0.000004470271,0.000007291747,0.00002584557,0.4641178,0.0008696741,0.531557,0.002062414,0.0001275376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006169973,0.0001405651,0.9907466,0.0002202696,0.0009849074,0.00008369939,0.000002164897,0.0003205939,0.001331203],"genre_scores_gemma":[0.5501709,3.935722e-7,0.4494991,0.00008350245,0.0002105615,0.000002706044,0.000002700707,0.000004697523,0.00002545321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5440009,"threshold_uncertainty_score":0.6359076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01327449925434027,"score_gpt":0.2962019672436924,"score_spread":0.2829274679893521,"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."}}