{"id":"W2251564431","doi":"","title":"On the Effectiveness of using Sentence Compression Models for Query-Focused Multi-Document Summarization","year":2012,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Automatic summarization; Computer science; Redundancy (engineering); Artificial intelligence; Cosine similarity; Natural language processing; Sentence; Relevance (law); Semantic similarity; Pattern recognition (psychology)","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":[0.003332604,0.00135327,0.001353798,0.00116774,0.0004132131,0.001316367,0.0009295762,0.00110268,0.001357726],"category_scores_gemma":[0.01136599,0.0003313096,0.0007711602,0.001201194,0.0004735861,0.003129936,0.0006099426,0.0009751795,0.0005905536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008091469,"about_ca_system_score_gemma":0.0008632783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003173823,"about_ca_topic_score_gemma":0.003720915,"domain_scores_codex":[0.9984537,0.0008477875,0.00008882716,0.0002462889,0.0002854996,0.00007779843],"domain_scores_gemma":[0.9915704,0.006780639,0.0003536687,0.0005301693,0.0006676119,0.0000975677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009880741,0.0003776071,0.002930536,0.0005629887,0.0003385794,0.0001361259,0.0002411091,0.5383378,0.02191386,0.006595445,0.003725856,0.4238521],"study_design_scores_gemma":[0.00003284167,0.0003153431,0.0006639878,0.00001899929,0.00008455633,0.00004676583,0.00003729973,0.989225,0.006501201,0.00231631,0.0007384143,0.00001929321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.176918,0.007281531,0.8059499,0.001446272,0.0001560721,0.0003435056,0.0004627952,0.002735994,0.004705888],"genre_scores_gemma":[0.7621002,0.002711338,0.2301464,0.0003079056,0.0002947226,0.0002301861,0.001540302,0.0002311818,0.002437659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003332604,"threshold_uncertainty_score":0.01762468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07576314842251103,"score_gpt":0.3027260897645275,"score_spread":0.2269629413420165,"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."}}