{"id":"W2803871820","doi":"10.1007/978-3-319-91947-8_48","title":"Cross-Language Text Summarization Using Sentence and Multi-Sentence Compression","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Agence Nationale de la Recherche","keywords":"Automatic summarization; Computer science; Natural language processing; Sentence; Artificial intelligence; Multi-document summarization","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007461807,0.0006048827,0.0004930084,0.000768951,0.0004931202,0.001327162,0.003005191,0.0004253662,0.00002521545],"category_scores_gemma":[0.0002234098,0.0005266714,0.00007831826,0.000672919,0.001619102,0.001475271,0.002829487,0.0008037561,0.000012882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002662618,"about_ca_system_score_gemma":0.000302587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001026037,"about_ca_topic_score_gemma":0.00005639155,"domain_scores_codex":[0.9959021,0.00004841645,0.0005493025,0.001877301,0.0009520653,0.0006708623],"domain_scores_gemma":[0.9973168,0.000247136,0.0004678742,0.001277448,0.0004992955,0.0001914808],"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":[0.0000225101,0.00007679815,0.001394468,0.0002635104,0.00001660538,0.0003470701,0.004739876,0.002622808,0.03135139,0.004792911,0.00002028096,0.9543518],"study_design_scores_gemma":[0.000266989,0.00009326214,0.0001362447,0.001345642,0.00000806257,0.0002089826,7.170196e-7,0.9477831,0.02046249,0.02886597,0.0000731621,0.0007553732],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001495644,0.003024777,0.9935184,0.0001150301,0.0008868529,0.0004025335,0.000007167103,0.0004358692,0.0001137755],"genre_scores_gemma":[0.09622793,0.00005032296,0.9024403,0.0006558715,0.0002724758,0.0000038537,0.000006838824,0.00003814273,0.0003042425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9535964,"threshold_uncertainty_score":0.9997185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02272415501754649,"score_gpt":0.3068379027972656,"score_spread":0.2841137477797191,"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."}}