{"id":"W4389520062","doi":"10.18653/v1/2023.findings-emnlp.499","title":"Reasoning Makes Good Annotators : An Automatic Task-specific Rules Distilling Framework for Low-resource Relation Extraction","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Zhejiang University; National Natural Science Foundation of China; National Key Research and Development Program of China; Ant Group; National Science Foundation","keywords":"Computer science; Task (project management); Relationship extraction; Pipeline (software); Relation (database); Exploit; Set (abstract data type); Artificial intelligence; Resource (disambiguation); Machine learning; Data mining; Labeled data; Natural language processing; Programming language","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":[0.004490582,0.002029925,0.001122396,0.003985579,0.001492352,0.002520707,0.003936437,0.002002512,0.004702118],"category_scores_gemma":[0.01188957,0.001025523,0.00286466,0.002245117,0.001107093,0.005781526,0.003806213,0.003669197,0.0050982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009813224,"about_ca_system_score_gemma":0.002730461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005351128,"about_ca_topic_score_gemma":0.01782483,"domain_scores_codex":[0.9962105,0.0009653009,0.0003067988,0.001612284,0.0007019433,0.0002032434],"domain_scores_gemma":[0.9943739,0.002427662,0.0003716764,0.001851075,0.0007289478,0.0002468769],"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":[0.0003311966,0.0004805825,0.004490833,0.0006347322,0.0002721386,0.0007548621,0.001685565,0.02571438,0.02927229,0.02826341,0.05380713,0.8542928],"study_design_scores_gemma":[0.0001042854,0.0001203765,0.001578471,0.0001472963,0.0002092314,0.0007077175,0.0003943981,0.8068177,0.02865673,0.08378363,0.07735533,0.000124933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006444475,0.0004662947,0.972138,0.0004131556,0.00008631263,0.0002347494,0.001488305,0.01710727,0.001621351],"genre_scores_gemma":[0.05762373,0.0002460445,0.9304918,0.0004290961,0.0000802629,0.0002539596,0.007325326,0.0009183806,0.002631451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005351128,"threshold_uncertainty_score":0.02374876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02842975542902074,"score_gpt":0.2863573737235161,"score_spread":0.2579276182944953,"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."}}