{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002015695,0.00133631,0.001457096,0.003564883,0.0007211671,0.002018362,0.001879737,0.001196556,0.006792794],"category_scores_gemma":[0.006214448,0.0003839127,0.00120129,0.004365251,0.0003983727,0.004217742,0.00136055,0.001391926,0.005460388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004194319,"about_ca_system_score_gemma":0.000965681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001466673,"about_ca_topic_score_gemma":0.001679577,"domain_scores_codex":[0.9983241,0.0006303431,0.000199864,0.0003331856,0.0004203239,0.00009215217],"domain_scores_gemma":[0.9966735,0.001874518,0.0002337571,0.0004469138,0.0006406414,0.0001307103],"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":[0.0005659402,0.0001737242,0.0006890494,0.0004990665,0.0001128497,0.000155006,0.0002259516,0.005545797,0.02293572,0.005442031,0.03048634,0.9331686],"study_design_scores_gemma":[0.0001855254,0.0008695738,0.003244599,0.0003249394,0.0005966049,0.0009647599,0.000461116,0.7904113,0.04917656,0.07716543,0.07638138,0.0002183001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01109536,0.001619493,0.9731184,0.0004286832,0.0003471216,0.0002562466,0.004244972,0.006903203,0.001986414],"genre_scores_gemma":[0.09605204,0.001352415,0.8809522,0.0003176759,0.0005818183,0.0006491212,0.0139658,0.0009614574,0.005167502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006792794,"threshold_uncertainty_score":0.02272415,"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."}}