{"id":"W3100949457","doi":"10.18653/v1/2020.findings-emnlp.127","title":"Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Filter (signal processing); Context (archaeology); Knowledge extraction; Conversation; Artificial intelligence; Process (computing); Task (project management); Persona; Information retrieval; Selection (genetic algorithm); Knowledge base; Natural language processing; Machine learning; Human–computer interaction; Computer vision; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003454733,0.002425676,0.00198602,0.002783118,0.001412303,0.001839244,0.003269998,0.002456227,0.004390241],"category_scores_gemma":[0.01068023,0.000695771,0.001521872,0.001334987,0.001122999,0.003863993,0.002711949,0.001931066,0.00368974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016022,"about_ca_system_score_gemma":0.001677312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008265651,"about_ca_topic_score_gemma":0.01382388,"domain_scores_codex":[0.9967445,0.00124123,0.0001607317,0.0009699971,0.0005181954,0.000365339],"domain_scores_gemma":[0.9958344,0.002176986,0.0002577252,0.0008025623,0.0006719442,0.0002564788],"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":[0.001673178,0.0009826008,0.008400897,0.001067946,0.0003522379,0.0008815827,0.004104061,0.03801377,0.05849234,0.01043893,0.02520956,0.8503829],"study_design_scores_gemma":[0.0001441314,0.0006249819,0.00432132,0.0001138995,0.000301673,0.0007119941,0.001577179,0.9146433,0.04010943,0.02215226,0.0151539,0.000145984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09046657,0.001762709,0.878701,0.0005312046,0.0001625202,0.0004507105,0.0006431454,0.02284957,0.004432497],"genre_scores_gemma":[0.62251,0.0003518065,0.3611943,0.0006517458,0.0001492082,0.0004032191,0.00303318,0.0008722908,0.01083424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008265651,"threshold_uncertainty_score":0.01827055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07232172618019449,"score_gpt":0.3008768054510579,"score_spread":0.2285550792708634,"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."}}