{"id":"W2062246499","doi":"10.5715/jnlp.18.217","title":"Construction of Context Models for Word Sense Disambiguation","year":2011,"lang":"en","type":"article","venue":"Journal of Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Word-sense disambiguation; Word (group theory); Context (archaeology); Computer science; SemEval; Natural language processing; Linguistics; Artificial intelligence; History; Philosophy; Engineering","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":[0.0005316641,0.0001570301,0.0003200879,0.0002823622,0.00008839907,0.00008653772,0.0004988497,0.0001001153,0.000003774301],"category_scores_gemma":[0.0002552972,0.0001187841,0.0001490577,0.0003597434,0.00008645147,0.002131446,0.00007288844,0.0003024684,2.869781e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006375062,"about_ca_system_score_gemma":0.0001502797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000170653,"about_ca_topic_score_gemma":0.000003735924,"domain_scores_codex":[0.9986148,0.0000483753,0.0006028604,0.0001827346,0.0003453591,0.0002059086],"domain_scores_gemma":[0.9976553,0.00008036972,0.001143714,0.0001826008,0.0008743394,0.0000637304],"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":[0.0001388565,0.00004730574,0.00002940822,0.0001682275,0.00002385317,0.00003023537,0.007970262,0.000009205583,0.01196671,0.005955367,0.00004736537,0.9736132],"study_design_scores_gemma":[0.002449863,0.0006277328,0.0001717179,0.002045569,0.0001675798,0.002456646,0.004624233,0.3913395,0.4457316,0.1494942,0.00008308125,0.0008082292],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03052673,0.04804249,0.920532,0.000150797,0.0003692677,0.0001635881,0.000002676048,0.00009890672,0.0001135019],"genre_scores_gemma":[0.5448838,0.00001000661,0.4549477,0.00006422441,0.000065623,0.000001717925,8.72706e-7,0.000007824378,0.00001826402],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972805,"threshold_uncertainty_score":0.4843874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02621211769329632,"score_gpt":0.2813093315516963,"score_spread":0.2550972138584,"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."}}