{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001794216,0.001481304,0.002463144,0.005132548,0.0006367547,0.001741842,0.001408328,0.001151072,0.003975546],"category_scores_gemma":[0.004086909,0.0005643963,0.001886671,0.006905077,0.0005293586,0.005744739,0.001504431,0.001476123,0.003260348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007374036,"about_ca_system_score_gemma":0.001400834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007398649,"about_ca_topic_score_gemma":0.007790507,"domain_scores_codex":[0.9979977,0.0005608291,0.0002329282,0.0004274407,0.0006356506,0.0001454245],"domain_scores_gemma":[0.998092,0.0009552284,0.000080657,0.0002521364,0.0005762929,0.00004363785],"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":[0.0005787929,0.0003585966,0.001150112,0.0006112618,0.0002751433,0.0001812571,0.0001967764,0.03313115,0.03661226,0.01155797,0.01714757,0.8981991],"study_design_scores_gemma":[0.00007253924,0.0001352006,0.0006964923,0.00003197141,0.0001689901,0.0002471847,0.0001047747,0.9563053,0.01471427,0.02059477,0.006861108,0.00006745756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01416638,0.002089459,0.975332,0.0002752573,0.0001552505,0.000155687,0.0008989827,0.005822051,0.00110488],"genre_scores_gemma":[0.191905,0.002254539,0.7927894,0.0003188952,0.0003203007,0.0004146193,0.006429416,0.0008066501,0.00476117],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007398649,"threshold_uncertainty_score":0.01471114,"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."}}