{"id":"W4205795307","doi":"10.1109/bigdata52589.2021.9671523","title":"BIRD-QA: A BERT-based Information Retrieval Approach to Domain Specific Question Answering","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Question answering; Information retrieval; Context (archaeology); Knowledge base; Preprocessor; Domain (mathematical analysis); Matching (statistics); Task (project management); F1 score; Language model; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001019689,0.0002704336,0.0002463904,0.0003429881,0.0001390869,0.001253427,0.005406965,0.000121025,0.00005697438],"category_scores_gemma":[0.0003266394,0.0002891323,0.00004072347,0.0006113512,0.00004150128,0.002903135,0.002076879,0.0003617874,0.0005335115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001819744,"about_ca_system_score_gemma":0.000608268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001611929,"about_ca_topic_score_gemma":0.0001644358,"domain_scores_codex":[0.9964506,0.0001554261,0.0006123121,0.001197706,0.001234913,0.0003490155],"domain_scores_gemma":[0.9949826,0.0001011691,0.0002090496,0.003978579,0.0005385084,0.0001901204],"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":[0.0002299142,0.0005218603,0.0003248932,0.00008669191,0.0001404043,0.0001107224,0.000699877,0.004140921,0.01048508,0.2683913,0.02099447,0.6938739],"study_design_scores_gemma":[0.0009329953,0.00005745946,0.0005716041,0.0002701648,0.00001064261,0.0000436507,0.0001677348,0.7981067,0.002594365,0.001482024,0.1951955,0.0005672041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003317104,0.00002539656,0.9822174,0.003997763,0.004962659,0.0002269331,0.001274326,0.0002071363,0.003771252],"genre_scores_gemma":[0.6360285,0.0001619352,0.3442138,0.002255265,0.002463188,0.00003134225,0.01458043,0.00005086718,0.0002146962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7939658,"threshold_uncertainty_score":0.9999743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2826899529421072,"score_gpt":0.3327089787810121,"score_spread":0.05001902583890488,"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."}}