{"id":"W2953152789","doi":"10.48550/arxiv.1809.01854","title":"Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Parsing; Syntax; Artificial intelligence; Abstract syntax tree; Machine translation; Natural language processing; Sentence; Tree (set theory); Recurrent neural network; Decoding methods; Artificial neural network; Neural decoding; Tree structure; Dependency grammar; Programming language; Data structure; Algorithm","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":[0.0009141846,0.0008964968,0.0005965587,0.0007147602,0.0005022357,0.001006002,0.00115753,0.001197591,0.005222325],"category_scores_gemma":[0.004200869,0.0005559916,0.0009895161,0.001179459,0.0006730933,0.002218988,0.0009129729,0.00191517,0.002429668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009495133,"about_ca_system_score_gemma":0.001414249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004297804,"about_ca_topic_score_gemma":0.008205637,"domain_scores_codex":[0.9994616,0.0002195428,0.00004185276,0.0001484183,0.00009750528,0.00003116105],"domain_scores_gemma":[0.9988636,0.000623735,0.00006737572,0.0002113116,0.0002067667,0.00002723007],"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":[0.0002155248,0.0001299554,0.0007044421,0.0004499357,0.0001404113,0.0003546123,0.0002384944,0.3848788,0.02337989,0.06434069,0.0138057,0.5113617],"study_design_scores_gemma":[0.00001064817,0.00003037308,0.0001095214,0.00001693746,0.00002184555,0.0000571896,0.00001161845,0.9466355,0.005675435,0.04492325,0.002494366,0.00001329318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009537557,0.0005600483,0.9828148,0.0003846147,0.0001103433,0.00004605973,0.0002839784,0.003342652,0.002919824],"genre_scores_gemma":[0.3518134,0.000963744,0.6362052,0.0004440798,0.0001502044,0.0002912716,0.001837407,0.0008022017,0.007492422],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005222325,"threshold_uncertainty_score":0.01747042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05470065587620791,"score_gpt":0.2180873751482772,"score_spread":0.1633867192720693,"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."}}