{"id":"W4385567355","doi":"10.18653/v1/2022.findings-emnlp.502","title":"Probing for Constituency Structure in Neural Language Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Treebank; Computer science; Natural language processing; Focus (optics); Artificial intelligence; Syntactic structure; Syntax; Tree structure; Parsing; Data structure; 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":[0.00171804,0.0007033273,0.0006138295,0.0004666652,0.0004209075,0.001062223,0.0008790968,0.0009853326,0.002024294],"category_scores_gemma":[0.00918738,0.0005700247,0.0007611582,0.0005940769,0.0006898048,0.004023766,0.001085646,0.002795945,0.0006314495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000696363,"about_ca_system_score_gemma":0.000489108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002056199,"about_ca_topic_score_gemma":0.004274948,"domain_scores_codex":[0.9993395,0.0003025792,0.00002523903,0.0002315102,0.00005128004,0.00004989428],"domain_scores_gemma":[0.9971485,0.002217605,0.0001458418,0.000321237,0.0001088309,0.00005793031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009357755,0.0002322872,0.01355816,0.0004094593,0.0003452607,0.0003122343,0.001324838,0.4904438,0.06642645,0.05124125,0.004147502,0.370623],"study_design_scores_gemma":[0.00000677926,0.00004814517,0.001076027,0.00001043922,0.00002264743,0.00002874734,0.00004610613,0.9752333,0.003614354,0.01931067,0.0005924397,0.00001023745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3716601,0.0005810472,0.622031,0.000705205,0.00006288364,0.00004603558,0.0002979524,0.002020887,0.002594973],"genre_scores_gemma":[0.9368664,0.0001956647,0.06015421,0.000146327,0.00003312342,0.00009520591,0.0007386128,0.0001799,0.001590593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002056199,"threshold_uncertainty_score":0.009086013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02351577902937655,"score_gpt":0.2507793196022692,"score_spread":0.2272635405728926,"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."}}