{"id":"W2104710058","doi":"10.1162/coli_r_00188","title":"<b>Semi-Supervised Learning and Domain Adaptation in Natural Language Processing</b> <b>Anders Søgaard</b> University of Copenhagen Morgan &amp; Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, volume 21), 2013, x+93 pp; paperbound, ISBN 978-1-60845-985-8, $40.00; e-book, ISBN 978-1-60845-986-5, $30.00 or by subscription","year":2014,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Machine learning; Parsing; Test set; Test data; Supervised learning; sort; Adaptation (eye); Information retrieval; Artificial neural network; Psychology","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"],"consensus_categories":[],"category_scores_codex":[0.0007011403,0.0004668038,0.0005375707,0.0003743141,0.0007155887,0.0003159328,0.0007424465,0.0003140711,0.0002631491],"category_scores_gemma":[0.002075553,0.0004855067,0.00009619858,0.0007463272,0.0003531743,0.0002772,0.0002228926,0.0007777901,0.00009295813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002534512,"about_ca_system_score_gemma":0.0002031212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004464576,"about_ca_topic_score_gemma":0.0002502321,"domain_scores_codex":[0.9967514,0.000439686,0.0006243933,0.000864913,0.0007902713,0.0005293197],"domain_scores_gemma":[0.9977615,0.0006982699,0.0005465489,0.0003564881,0.0004859427,0.0001512128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002432618,0.002414603,0.006261586,0.001853189,0.0006623698,0.0004803151,0.08609911,0.1861687,0.05948982,0.0201796,0.4329876,0.2009705],"study_design_scores_gemma":[0.00295074,0.0003958239,0.002858226,0.0003427101,0.000067478,0.00001883185,0.006272655,0.6628407,0.0005533469,0.0009270851,0.3216417,0.001130731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1059594,0.01139505,0.8742487,0.00156469,0.0008945236,0.001194376,0.0001374166,0.001498032,0.003107854],"genre_scores_gemma":[0.9590173,0.000116605,0.0369558,0.0003107226,0.0001656867,0.00001018986,0.0006096225,0.00005743586,0.002756621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8530579,"threshold_uncertainty_score":0.9997597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01448030735680526,"score_gpt":0.2444919814516998,"score_spread":0.2300116740948945,"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."}}