{"id":"W2293834552","doi":"10.3115/v1/n15-1099","title":"A Word Embedding Approach to Predicting the Compositionality of Multiword Expressions","year":2015,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Australian Research Council; Australian Government","keywords":"Principle of compositionality; Computer science; Natural language processing; Word embedding; Artificial intelligence; Embedding; Word (group theory); Linguistics","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":[0.001108144,0.001426376,0.000626452,0.003302761,0.0004825056,0.001074962,0.0007028952,0.0009230967,0.002158452],"category_scores_gemma":[0.00575297,0.0003070286,0.0009777187,0.002870206,0.0004405149,0.004481031,0.001302618,0.001496551,0.001607091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003486746,"about_ca_system_score_gemma":0.0005681956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001327292,"about_ca_topic_score_gemma":0.002154475,"domain_scores_codex":[0.9990966,0.0002970655,0.00010174,0.0002801872,0.0001654417,0.00005895153],"domain_scores_gemma":[0.9975032,0.001123742,0.0003079422,0.0003731577,0.0005868614,0.0001050521],"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":[0.0005723421,0.0004493927,0.01623201,0.0008002159,0.0003470889,0.0002794026,0.0008293414,0.01798598,0.03948967,0.01252391,0.007636482,0.9028542],"study_design_scores_gemma":[0.0000629796,0.0006148095,0.01102431,0.0001337388,0.0003089582,0.0009818277,0.0008533575,0.9027481,0.02037184,0.04547929,0.01728232,0.0001383792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1591994,0.002671454,0.8284865,0.0004199452,0.0003684165,0.0002679045,0.002269174,0.002705746,0.003611387],"genre_scores_gemma":[0.5917516,0.001385868,0.3952719,0.0001598281,0.0002708916,0.0003538343,0.00632068,0.0003372626,0.004148102],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003302761,"threshold_uncertainty_score":0.007220805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08948264642058708,"score_gpt":0.315643657633515,"score_spread":0.226161011212928,"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."}}