{"id":"W2397197605","doi":"10.1111/coin.12094","title":"Improving Shift‐Reduce Phrase‐Structure Parsing with Constituent Boundary Information","year":2016,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"National Natural Science Foundation of China; Ministry of Education - Singapore","keywords":"Parsing; Computer science; Parser combinator; Artificial intelligence; Classifier (UML); Top-down parsing; Phrase; Bottom-up parsing; Natural language processing; Boundary (topology); LR parser; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001436932,0.0001710725,0.0001224014,0.0001561875,0.0002079037,0.0003819409,0.0007023952,0.00006287594,0.00002521648],"category_scores_gemma":[0.00009358687,0.0001107014,0.00003057829,0.0003520276,0.0002071913,0.002563726,0.0001784283,0.0001431627,0.00004344049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338149,"about_ca_system_score_gemma":0.0003344799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001870965,"about_ca_topic_score_gemma":0.000003827124,"domain_scores_codex":[0.9987335,0.00003265967,0.0002935069,0.0002859439,0.0004141865,0.0002402598],"domain_scores_gemma":[0.9990005,0.0001656216,0.0002026507,0.0002567336,0.0002895738,0.00008486342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001959041,0.00001503917,0.0001458792,0.00003468669,0.00001226394,0.00001260342,0.0006079751,0.001382139,0.001289776,0.2591932,0.0001379094,0.7371489],"study_design_scores_gemma":[0.0003538368,0.0002313557,0.0006011557,0.0007243085,0.00001672652,0.0004568268,0.00007378122,0.1461882,0.1451876,0.703708,0.001504166,0.0009540817],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005282856,0.0003065934,0.9924263,0.001093158,0.0001966941,0.0001575079,0.00001175273,0.0004288366,0.00009634339],"genre_scores_gemma":[0.5981736,0.000001900746,0.4014279,0.000340231,0.00002992068,0.000005272724,0.000007717507,0.00000409798,0.000009369849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7361949,"threshold_uncertainty_score":0.4514274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01100947696729179,"score_gpt":0.2611931464031279,"score_spread":0.2501836694358361,"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."}}