{"id":"W2582886532","doi":"10.1609/aaai.v31i1.11111","title":"Discovering Conversational Dependencies between Messages in Dialogs","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Probabilistic logic; Classifier (UML); Task (project management); Set (abstract data type); Customer service; Artificial intelligence; Information retrieval; Heuristic; Online chat; Service (business); World Wide Web; The Internet","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":[0.001569646,0.001084506,0.0006897479,0.002690762,0.001204493,0.001034557,0.0008271557,0.0009847662,0.001367754],"category_scores_gemma":[0.009615527,0.0005346956,0.0006803939,0.001020066,0.0004075477,0.002659935,0.000974048,0.001337339,0.001078787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006091819,"about_ca_system_score_gemma":0.001139288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007282442,"about_ca_topic_score_gemma":0.01142543,"domain_scores_codex":[0.9986614,0.0004305365,0.00008052265,0.0004334344,0.0002516269,0.0001424833],"domain_scores_gemma":[0.9908209,0.006998223,0.000734719,0.0003297734,0.0007925798,0.0003237938],"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":[0.002232578,0.001813874,0.184514,0.001222799,0.000406623,0.001930597,0.005724302,0.05300434,0.08001211,0.006409117,0.01249752,0.6502321],"study_design_scores_gemma":[0.00003662512,0.0002383494,0.05752061,0.0000698412,0.0001792772,0.0004164266,0.000810169,0.910394,0.01586131,0.009139872,0.005268011,0.00006565342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.708367,0.002329317,0.2767064,0.0009580941,0.0001043607,0.0003127857,0.00328716,0.002161723,0.005773199],"genre_scores_gemma":[0.9552625,0.000345511,0.04014258,0.00007560337,0.0001413702,0.0001061337,0.002525353,0.00007729173,0.001323694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007282442,"threshold_uncertainty_score":0.01448011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.120334447327698,"score_gpt":0.3256685017205043,"score_spread":0.2053340543928063,"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."}}