{"id":"W1542447206","doi":"10.1007/3-540-45399-7_13","title":"Using Information Extraction and Natural Language Generation to Answer E-Mail","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information extraction; Natural language; Natural language generation; Question answering; Natural language processing; Artificial intelligence; World Wide Web; 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":[0.001702228,0.00102735,0.0009035902,0.002588041,0.0008229433,0.001572631,0.001386659,0.001370746,0.007571445],"category_scores_gemma":[0.006826243,0.0006072107,0.001134896,0.001642063,0.0006056172,0.002694722,0.001098016,0.0009967069,0.004267918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005674033,"about_ca_system_score_gemma":0.0008234595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001616341,"about_ca_topic_score_gemma":0.002112371,"domain_scores_codex":[0.9984138,0.0006815713,0.0001437751,0.0003088745,0.0003698867,0.00008198609],"domain_scores_gemma":[0.9955279,0.003271027,0.0001774886,0.0003017582,0.0006705045,0.0000512793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003873983,0.0004464298,0.001784837,0.0006850071,0.00009632931,0.0006802002,0.0006859916,0.0110064,0.03792401,0.02002219,0.02866627,0.8976149],"study_design_scores_gemma":[0.0003298819,0.0003834895,0.001855305,0.0001709498,0.0003652081,0.00124196,0.0005257194,0.6912895,0.1338395,0.1077874,0.06208833,0.0001226969],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0258674,0.0005892824,0.9435841,0.0007201931,0.0002341566,0.0005294952,0.001091407,0.01975964,0.007624313],"genre_scores_gemma":[0.1254702,0.0003563134,0.8635451,0.0003127083,0.0001493168,0.0003322562,0.003961285,0.0006298284,0.005242934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007571445,"threshold_uncertainty_score":0.02532905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768209204753136,"score_gpt":0.2880871722393515,"score_spread":0.2704050801918202,"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."}}