{"id":"W2904760604","doi":"10.1609/aaai.v33i01.33016188","title":"Enriching Word Embeddings with a Regressor Instead of Labeled Corpora","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vetenskapsrådet","keywords":"Computer science; Natural language processing; Artificial intelligence; Word (group theory); Lexicon; Task (project management); Embedding; Sentence; SemEval; Word embedding; Analogy; Binary classification; Linguistics; Support vector machine","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":[0.002319519,0.002118485,0.001045516,0.002364436,0.0006043541,0.001643724,0.001374109,0.001029226,0.003902567],"category_scores_gemma":[0.01344468,0.0007583957,0.0007617848,0.002462828,0.0007702289,0.00773088,0.002881254,0.002251119,0.006540991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004905641,"about_ca_system_score_gemma":0.001294035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001829312,"about_ca_topic_score_gemma":0.006015721,"domain_scores_codex":[0.9981438,0.0007389184,0.0001386311,0.0005662267,0.0003244473,0.00008800097],"domain_scores_gemma":[0.9945143,0.001860121,0.0004970058,0.001873789,0.00111904,0.0001357468],"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":[0.0003451218,0.0007079202,0.0109211,0.0006991458,0.000223593,0.0002513152,0.0006889406,0.03451774,0.06224466,0.01646953,0.02431602,0.8486149],"study_design_scores_gemma":[0.00007628378,0.0004660993,0.004334386,0.0001995303,0.0001845752,0.0004953316,0.0006242704,0.7724243,0.08025922,0.06029651,0.08046087,0.000178515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02897238,0.0003855213,0.9553441,0.0004247428,0.0001712074,0.0001362759,0.001745348,0.009922393,0.002898115],"genre_scores_gemma":[0.2079746,0.0005746546,0.7695757,0.0003828228,0.0001624453,0.0005504356,0.01151033,0.00152724,0.007741793],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003902567,"threshold_uncertainty_score":0.01305532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05268464246031737,"score_gpt":0.2704866470360274,"score_spread":0.2178020045757101,"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."}}