{"id":"W2119029180","doi":"10.1109/icassp.1994.389724","title":"Learning consistent semantics from training data","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Utterance; Computer science; Context (archaeology); Sentence; Task (project management); Component (thermodynamics); Programmer; Semantics (computer science); Artificial intelligence; Natural language processing; Parsing; Natural language; Representation (politics); Word (group theory); Programming language; Linguistics","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":[0.003785634,0.002786726,0.001809755,0.002880911,0.0009353586,0.00282299,0.00328201,0.002366487,0.005101793],"category_scores_gemma":[0.01848943,0.001182325,0.002064845,0.002083948,0.001573428,0.006022788,0.002249144,0.004042502,0.002668753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001377706,"about_ca_system_score_gemma":0.00234453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002921925,"about_ca_topic_score_gemma":0.006239195,"domain_scores_codex":[0.996744,0.00103837,0.000223896,0.001376587,0.0004534097,0.0001637516],"domain_scores_gemma":[0.9894195,0.007414788,0.0003501923,0.001891031,0.000771973,0.0001525436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007431154,0.0006787991,0.007813914,0.0009039338,0.0004333119,0.0006453331,0.0005230951,0.1738077,0.007359029,0.01688329,0.02199334,0.7682152],"study_design_scores_gemma":[0.0001518386,0.0002214057,0.0009353514,0.0001583778,0.0001235344,0.0001565437,0.0003358055,0.8803619,0.008429357,0.1002217,0.008862754,0.00004129203],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06866883,0.001591905,0.9068879,0.001514418,0.000264814,0.0003264351,0.005142006,0.01129628,0.004307423],"genre_scores_gemma":[0.5621454,0.0009521805,0.4003584,0.0008016011,0.0002776834,0.0008183102,0.03049424,0.0009841088,0.003167978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005101793,"threshold_uncertainty_score":0.0200206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1058448855710648,"score_gpt":0.2885465545130879,"score_spread":0.1827016689420231,"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."}}