{"id":"W2407223942","doi":"","title":"Discourse Relation Recognition by Comparing Various Units of Sentence Expression with Recursive Neural Network","year":2015,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; Institute for Catastrophic Loss Reduction; University of Pennsylvania","keywords":"Sentence; Computer science; Relation (database); Meaning (existential); Natural language processing; Feature (linguistics); Artificial intelligence; Recurrent neural network; Expression (computer science); Word (group theory); Artificial neural network; Speech recognition; Linguistics; Psychology; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003165029,0.0001931495,0.000207776,0.00007837672,0.0003035178,0.0001432497,0.0005259668,0.00008023104,0.000001024291],"category_scores_gemma":[0.0003046666,0.0001580244,0.00002424253,0.0007413923,0.0002638687,0.002727418,0.0003224344,0.0002895024,0.000003113225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001632747,"about_ca_system_score_gemma":0.0003825088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003718557,"about_ca_topic_score_gemma":0.00002712757,"domain_scores_codex":[0.9981508,0.0001166269,0.0003445472,0.0004342159,0.000708307,0.0002454715],"domain_scores_gemma":[0.9981062,0.0001007452,0.0003453363,0.0004943627,0.0008057936,0.0001475325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004159809,0.001643529,0.07689261,0.0006869471,0.0003644215,0.001955469,0.01060905,0.03121207,0.09516206,0.6513734,0.0826302,0.04331039],"study_design_scores_gemma":[0.005980485,0.002589305,0.002156817,0.01378791,0.0003212526,0.004548493,0.001697388,0.08646584,0.7804782,0.08734374,0.01068798,0.003942579],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1646624,0.001510059,0.8311656,0.0002147322,0.001159522,0.0002738789,0.00009288768,0.0003835827,0.0005373392],"genre_scores_gemma":[0.7259238,0.000008035506,0.2731919,0.0000418748,0.0002054773,0.00002042211,0.0005728027,0.00000834563,0.00002730035],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6853161,"threshold_uncertainty_score":0.6444049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03381629410901837,"score_gpt":0.2725006151502351,"score_spread":0.2386843210412167,"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."}}