{"id":"W2251385272","doi":"","title":"Cross-lingual Discourse Relation Analysis: A corpus study and a semi-supervised classification system","year":2014,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Relation (database); Natural language processing; Artificial intelligence; Divergence (linguistics); Task (project management); Linguistics; Discourse analysis; Annotation; Corpus linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0006897794,0.0001185708,0.0001893985,0.0002035396,0.0001664889,0.0003757043,0.0004328945,0.00006911014,0.00000343776],"category_scores_gemma":[0.000100467,0.00009873479,0.00004362922,0.0007120575,0.0000465438,0.0004589887,0.0001336808,0.0001405442,0.000005231975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005540421,"about_ca_system_score_gemma":0.0000255712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002387287,"about_ca_topic_score_gemma":0.00001451406,"domain_scores_codex":[0.9987282,0.0001516372,0.0002417064,0.0004299479,0.0002939952,0.0001545268],"domain_scores_gemma":[0.9990485,0.00007333829,0.0001462691,0.0005419926,0.0001259227,0.00006402634],"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":[0.00006576766,0.0004954732,0.2934894,0.0002174772,0.0004195934,0.00003321564,0.01579618,0.00008248653,0.06113793,0.2758842,0.00009721077,0.3522811],"study_design_scores_gemma":[0.0005674762,0.0001913837,0.0669692,0.00005939019,0.0002128382,0.00001596314,0.000665301,0.9216211,0.002528527,0.006841427,0.00002829014,0.0002991299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5687056,0.0001077654,0.4294908,0.0001326766,0.00005964666,0.0002057599,0.000001011747,0.0005400996,0.0007565696],"genre_scores_gemma":[0.9237226,0.000001095078,0.07608011,0.00002943236,0.00004672263,0.00003013794,0.000004865965,0.000007047018,0.00007799139],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9215386,"threshold_uncertainty_score":0.4026288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0168734560851954,"score_gpt":0.3060699483211083,"score_spread":0.2891964922359129,"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."}}