{"id":"W1506516332","doi":"10.1007/978-3-540-73351-5_22","title":"Combining Vector Space Model and Multi Word Term Extraction for Semantic Query Expansion","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Ranking (information retrieval); Computer science; Vector space model; Margin (machine learning); Artificial intelligence; Semantic similarity; Term (time); Word (group theory); Natural language processing; Cluster analysis; Similarity (geometry); Space (punctuation); Vector space; Information retrieval; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001002262,0.0005716131,0.0006261806,0.001171012,0.0003510072,0.0004121348,0.001532191,0.0003938226,0.000001697778],"category_scores_gemma":[0.0001140512,0.0005516978,0.0001567709,0.0004806208,0.0004677286,0.001108586,0.0008551247,0.0007144255,0.000003376151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000319039,"about_ca_system_score_gemma":0.0002340611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001485002,"about_ca_topic_score_gemma":0.0001555713,"domain_scores_codex":[0.996327,0.00002116901,0.000559453,0.001719538,0.0006998227,0.0006730349],"domain_scores_gemma":[0.9973058,0.0006564818,0.0004331789,0.001147633,0.0002809577,0.000175982],"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":[0.00001593497,0.00005057953,0.00005783765,0.00008241246,0.0000157717,0.00004033813,0.0007829811,0.04079197,0.005948209,0.01517811,0.00000911232,0.9370267],"study_design_scores_gemma":[0.0002714402,0.0001005737,0.0001115527,0.0004155035,0.00001710721,0.00004159282,2.751278e-7,0.9174881,0.004988831,0.07588357,0.00009255928,0.0005889161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004530317,0.0004112916,0.9971739,0.0002629142,0.0005061537,0.0006399085,0.00000255975,0.0003744022,0.0001758202],"genre_scores_gemma":[0.1882419,0.00007442426,0.8108493,0.0003760433,0.000138341,0.00001769961,0.000004399813,0.00004080488,0.0002570836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9364378,"threshold_uncertainty_score":0.9996935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03547433304624778,"score_gpt":0.3152286062239996,"score_spread":0.2797542731777518,"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."}}