{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001318173,0.000999099,0.001354941,0.00234301,0.0007513415,0.002072683,0.001726645,0.001093398,0.007125287],"category_scores_gemma":[0.007350111,0.0005845577,0.001412139,0.003031116,0.0006425502,0.003899602,0.001821655,0.002149877,0.003075319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073964,"about_ca_system_score_gemma":0.001522346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003166601,"about_ca_topic_score_gemma":0.006801802,"domain_scores_codex":[0.9983819,0.0006104761,0.0001220893,0.0003994136,0.0003449561,0.0001412293],"domain_scores_gemma":[0.9958835,0.002733088,0.0002074022,0.0006624141,0.0004270206,0.00008657188],"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":[0.0006719765,0.0004742393,0.0009825133,0.0005647122,0.0001640167,0.0003801992,0.00033612,0.1493248,0.007847724,0.05890754,0.04374033,0.7366058],"study_design_scores_gemma":[0.00006137648,0.00007205886,0.0001964872,0.00005107648,0.00004599556,0.00008621225,0.0001366372,0.8668408,0.004637112,0.1223956,0.005452924,0.00002368197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02524086,0.001540122,0.9549929,0.001402185,0.0004538837,0.0002378173,0.002047318,0.009566061,0.004518735],"genre_scores_gemma":[0.176428,0.0005604925,0.8078128,0.000516843,0.0003774927,0.000394935,0.006822181,0.001549141,0.005538223],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007125287,"threshold_uncertainty_score":0.02383649,"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."}}