{"id":"W4225102708","doi":"10.18653/v1/2022.naacl-main.212","title":"Document-Level Relation Extraction with Sentences Importance Estimation and Focusing","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; DeepMind; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Sentence; Computer science; Relationship extraction; Focus (optics); Natural language processing; Artificial intelligence; Relation (database); Variety (cybernetics); Graph; Sequence (biology); Information extraction; Data mining; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003825435,0.0001141543,0.0001959305,0.00009568693,0.0004409595,0.00004493072,0.001010178,0.00002526035,0.000001554792],"category_scores_gemma":[0.001233777,0.0000748831,0.00008058687,0.0003789125,0.0002333605,0.0001210402,0.0006327276,0.0002006513,4.606829e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000129079,"about_ca_system_score_gemma":0.00005477298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001127841,"about_ca_topic_score_gemma":0.00004875654,"domain_scores_codex":[0.9986397,0.00001883035,0.0003795432,0.0002216856,0.0006141486,0.0001260708],"domain_scores_gemma":[0.9966852,0.0001592926,0.002231901,0.0002028676,0.0007112348,0.000009472837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00004359141,0.00007391999,0.4191085,0.0001450899,0.0001701338,1.650732e-7,0.004163081,0.05110892,0.002503345,0.5050189,0.00004938391,0.01761495],"study_design_scores_gemma":[0.0009359147,0.0004343982,0.3790823,0.0002319784,0.000222492,0.00001367889,0.008631872,0.3508357,0.01250985,0.2464917,0.0001243696,0.0004858322],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9817568,0.00004719545,0.01555352,0.001637493,0.000193892,0.0004774975,0.00004785904,0.00008181643,0.0002039327],"genre_scores_gemma":[0.9725477,0.000002681111,0.0272907,0.0000253037,0.00001839112,0.00002910236,0.000003192238,0.000007079019,0.00007591454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2997268,"threshold_uncertainty_score":0.3391549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01931482882584975,"score_gpt":0.2540263137987291,"score_spread":0.2347114849728793,"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."}}