{"id":"W1590732297","doi":"10.1007/11766247_28","title":"Beyond the Bag of Words: A Text Representation for Sentence Selection","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Selection (genetic algorithm); Sentence; Natural language processing; Representation (politics); Artificial intelligence; Computer science; Linguistics; Psychology; Political science; Philosophy","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":[0.0005975334,0.0002801489,0.000302001,0.0005674522,0.0002533799,0.0003038354,0.002527498,0.0002142583,0.000006453923],"category_scores_gemma":[0.0001452268,0.0002095903,0.0001259356,0.0008901266,0.0007334542,0.0005336713,0.0005253655,0.0003425306,0.000006410556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000154317,"about_ca_system_score_gemma":0.000238673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003514198,"about_ca_topic_score_gemma":0.00006462207,"domain_scores_codex":[0.9975155,0.00002298428,0.0005024218,0.0009587237,0.000653207,0.0003471773],"domain_scores_gemma":[0.9974409,0.0006498548,0.000494964,0.001056281,0.0003240644,0.00003399021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008364235,0.00003090997,0.0001674701,0.00003304829,0.00001007741,0.000001685572,0.0003681072,0.01562145,0.001103343,0.1354791,0.0005420576,0.8466344],"study_design_scores_gemma":[0.0002508418,0.0001719816,0.0004030835,0.0001067743,0.00001095389,0.00001861967,0.000001243924,0.3961002,0.01877122,0.581543,0.002268537,0.0003535966],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009931877,0.000220948,0.9937271,0.002705298,0.0007127078,0.0006531152,0.000004551568,0.0001971406,0.001679814],"genre_scores_gemma":[0.443874,0.00005708846,0.5530033,0.000705137,0.0003319024,0.00009466514,0.00001363155,0.00003080902,0.001889459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8462808,"threshold_uncertainty_score":0.8546847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02034437246250105,"score_gpt":0.2677130004816878,"score_spread":0.2473686280191868,"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."}}