{"id":"W2953772283","doi":"10.22215/etd/2019-13514","title":"Representation Learning for Information Extraction","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Terminology; Information extraction; Bridging (networking); Sentence; Task (project management); Domain (mathematical analysis); Information retrieval","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":[0.002149222,0.0009517809,0.0007831801,0.002191263,0.0005369936,0.002609753,0.00125125,0.001100505,0.00546985],"category_scores_gemma":[0.009975241,0.0003945013,0.001480662,0.003260766,0.001003048,0.004899264,0.002559916,0.002608972,0.003341538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001347727,"about_ca_system_score_gemma":0.001425328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001618039,"about_ca_topic_score_gemma":0.002017989,"domain_scores_codex":[0.9980099,0.000769439,0.0001703508,0.0005341459,0.0004146663,0.0001015928],"domain_scores_gemma":[0.9970806,0.001391904,0.0001689338,0.0009416955,0.0003673657,0.00004943273],"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":[0.00008255614,0.00008957137,0.0006150085,0.0006558609,0.0001527849,0.00007351438,0.000184457,0.02681709,0.004608123,0.1530354,0.01730471,0.7963811],"study_design_scores_gemma":[0.00003738713,0.00009524713,0.0006507874,0.0002539917,0.00008470179,0.0001718855,0.0001268226,0.3517152,0.009600873,0.5893851,0.04783337,0.00004469264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003756079,0.002013884,0.9870729,0.0009117494,0.0001116178,0.0001076753,0.000873664,0.001390253,0.003762084],"genre_scores_gemma":[0.1767307,0.004318909,0.8020564,0.0005691655,0.000346698,0.0006576036,0.007123805,0.0003454175,0.007851458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00546985,"threshold_uncertainty_score":0.01829851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01285625751225062,"score_gpt":0.3350664069681976,"score_spread":0.3222101494559469,"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."}}