{"id":"W2099050228","doi":"10.3115/v1/w15-0909","title":"The Impact of Multiword Expression Compositionality on Machine Translation Evaluation","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Principle of compositionality; Computer science; Machine translation; Natural language processing; Metric (unit); Artificial intelligence; Translation (biology); Expression (computer science); Programming language","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":[0.001009651,0.00006574049,0.00006276301,0.00003688364,0.00007280843,0.00005154539,0.0003458768,0.00003273147,0.000006745194],"category_scores_gemma":[0.00007844661,0.00003379733,0.00004700253,0.000147716,0.00002422129,0.0002786742,0.00003714625,0.00007382124,0.000002713155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007688331,"about_ca_system_score_gemma":0.0000723129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001356943,"about_ca_topic_score_gemma":0.000007913002,"domain_scores_codex":[0.9990324,0.0001592012,0.0001438013,0.0001275858,0.0004592301,0.00007773132],"domain_scores_gemma":[0.9992095,0.0001373017,0.00008693429,0.0002743195,0.0002534093,0.00003858212],"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":[0.0001999776,0.0002295794,0.0007672436,0.000008978684,0.00001948672,9.359849e-7,0.001192128,0.002274105,0.07049373,0.0247142,0.002312122,0.8977875],"study_design_scores_gemma":[0.0004502755,0.0001989505,0.001727266,0.00003299552,0.000003458279,0.000003006261,0.00000664659,0.7946726,0.1259815,0.07679799,0.00003870433,0.00008665404],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03078533,0.001864485,0.9633673,0.0009177054,0.00008241153,0.0003523526,0.000003912863,0.0002531603,0.002373287],"genre_scores_gemma":[0.8259652,0.000001706453,0.1739684,0.00002263594,0.00001193135,0.000007705306,0.000008657628,0.000002170401,0.00001153534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8977008,"threshold_uncertainty_score":0.1378215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07300703251397235,"score_gpt":0.3963109459968595,"score_spread":0.3233039134828871,"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."}}