{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005354884,0.00006460731,0.00009291859,0.00003538611,0.0000905128,0.00004775309,0.0007101572,0.00002413071,0.000002736615],"category_scores_gemma":[0.000090626,0.00004149498,0.00003318625,0.0002016842,0.0000195784,0.0001793938,0.0004829791,0.00008615873,0.000005015304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002326793,"about_ca_system_score_gemma":0.00004567956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009996945,"about_ca_topic_score_gemma":0.000002438617,"domain_scores_codex":[0.9990575,0.00007447234,0.0001992038,0.0002195403,0.0003050205,0.0001443209],"domain_scores_gemma":[0.9991315,0.0001165603,0.00005179547,0.0004901309,0.000098559,0.000111466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003033323,0.0005741336,0.009393431,0.00005493065,0.00006138534,0.00000273027,0.04715867,0.5022173,0.008157562,0.3880764,0.005430148,0.03884301],"study_design_scores_gemma":[0.0001364242,0.000009986803,0.0007704442,0.00002426954,0.000002102422,0.00000486594,0.0005520823,0.9957122,0.0007531853,0.001535447,0.0004351928,0.00006380265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07066087,0.00001601687,0.912195,0.0007520888,0.0001207077,0.0001495634,0.000001083771,0.00008991015,0.01601472],"genre_scores_gemma":[0.6133583,9.974668e-8,0.3863285,0.0001671928,0.00003687608,0.00001287719,5.191706e-7,0.000001977554,0.0000936497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5426974,"threshold_uncertainty_score":0.1692116,"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."}}