{"id":"W2805287993","doi":"10.18653/v1/w18-1704","title":"Multi-Sentence Compression with Word Vertex-Labeled Graphs and Integer Linear Programming","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Sentence; Integer programming; Vertex (graph theory); Graph; Word (group theory); Combinatorics; Integer (computer science); Data compression; Natural language processing; Artificial intelligence; Discrete mathematics; Programming language; Theoretical computer science; Algorithm; 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":[0.0002976832,0.0004437388,0.0004103092,0.0002406329,0.0001680128,0.0005341572,0.001704275,0.0003216733,0.00000840426],"category_scores_gemma":[0.000073863,0.0002921647,0.0000625726,0.000355989,0.0002791696,0.0004061016,0.003442861,0.0009224902,0.000007445867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000420555,"about_ca_system_score_gemma":0.0001071229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002095586,"about_ca_topic_score_gemma":0.00006549101,"domain_scores_codex":[0.9976352,0.00007850276,0.0003174273,0.001134778,0.0004189822,0.0004150372],"domain_scores_gemma":[0.9980667,0.00006927314,0.0002687162,0.001036603,0.0004018264,0.0001569038],"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":[0.0002300533,0.0008811213,0.007619988,0.001852992,0.0003003927,0.0003665114,0.004627073,0.0000181817,0.01141736,0.01379295,0.003104388,0.955789],"study_design_scores_gemma":[0.002623223,0.0009865282,0.001050696,0.01171665,0.0001398478,0.0003541187,0.0001766224,0.8182506,0.09592336,0.06200591,0.002715129,0.004057297],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01818411,0.002398085,0.9755851,0.0003523589,0.0003259912,0.0007237094,0.000002097392,0.002355938,0.00007259662],"genre_scores_gemma":[0.1796259,0.00005125822,0.8197376,0.0001978157,0.00002609053,0.00006709158,0.000009030014,0.00002533435,0.0002599456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9517317,"threshold_uncertainty_score":0.999953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02288828558664156,"score_gpt":0.2949515939252628,"score_spread":0.2720633083386212,"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."}}