{"id":"W4386694320","doi":"10.48550/arxiv.2309.04919","title":"The Emergence of Chunking Structures with Hierarchical RNN","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Alberta","keywords":"Chunking (psychology); Computer science; Artificial intelligence; Natural language processing; Parsing; Sentence; Recurrent neural network; Conditional random field; Task (project management); Phrase; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001064906,0.0005643172,0.0003808729,0.0003538853,0.0003530741,0.0004302697,0.001043807,0.0005507258,0.0007295986],"category_scores_gemma":[0.004662456,0.0005613027,0.0003979245,0.000403768,0.0007189449,0.001766139,0.000843344,0.001286805,0.0003998547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007344629,"about_ca_system_score_gemma":0.0006184652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005728427,"about_ca_topic_score_gemma":0.009950676,"domain_scores_codex":[0.9995572,0.0001746428,0.00002410399,0.0001430975,0.00006486785,0.0000361556],"domain_scores_gemma":[0.9978362,0.001245434,0.0001917807,0.0004192122,0.000259613,0.00004783416],"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":[0.0002623562,0.0001198635,0.003574486,0.0002436974,0.0001492155,0.000354025,0.001096715,0.4941311,0.07942618,0.03179345,0.003922538,0.3849263],"study_design_scores_gemma":[0.000004736296,0.00002620489,0.0003438815,0.000006298134,0.000009612882,0.00001926832,0.00001699356,0.9814683,0.005536355,0.01202028,0.0005404954,0.000007474377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06492671,0.0003554743,0.9306045,0.0002030275,0.0000361806,0.00005500707,0.0001087885,0.001988141,0.00172203],"genre_scores_gemma":[0.6567208,0.0002365707,0.339414,0.0001463394,0.00003756108,0.0001330978,0.0004170083,0.0002817077,0.002612925],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005728427,"threshold_uncertainty_score":0.01139015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05803162169777708,"score_gpt":0.2100960288682787,"score_spread":0.1520644071705017,"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."}}