{"id":"W4307751734","doi":"10.3390/app122111038","title":"Framework for Handling Rare Word Problems in Neural Machine Translation System Using Multi-Word Expressions","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Machine translation; Fluency; Word (group theory); Test set; Set (abstract data type); Word embedding; Vocabulary; Translation (biology); Embedding; Linguistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001509781,0.0007932456,0.0008585557,0.00107764,0.001006979,0.001619817,0.001972345,0.001103216,0.004825246],"category_scores_gemma":[0.001742574,0.0004598298,0.001418293,0.0008544743,0.0008855091,0.001982991,0.001582572,0.001528526,0.001981845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001045275,"about_ca_system_score_gemma":0.00256942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009112061,"about_ca_topic_score_gemma":0.01025476,"domain_scores_codex":[0.9989428,0.0002799763,0.0001246039,0.0003003837,0.0002486703,0.0001036849],"domain_scores_gemma":[0.9995597,0.0001301559,0.0000449698,0.00005553992,0.0001833628,0.00002626968],"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":[0.0001754249,0.0002239402,0.001755565,0.00051874,0.0001690387,0.001559469,0.0008274172,0.4476537,0.01959746,0.2265313,0.00679933,0.2941885],"study_design_scores_gemma":[0.00002242288,0.00007662735,0.0001988184,0.00003402378,0.00004752762,0.0001925071,0.00006082848,0.9507191,0.002961969,0.03811044,0.007553529,0.00002215226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002733456,0.0002512432,0.9935892,0.0002420066,0.00005205614,0.0001016746,0.00005919522,0.0007302225,0.002240935],"genre_scores_gemma":[0.1673171,0.0008511153,0.8210146,0.0002476709,0.0001705645,0.0007621312,0.0005042136,0.000249841,0.0088828],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009112061,"threshold_uncertainty_score":0.01811802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0708010812538504,"score_gpt":0.327040812905348,"score_spread":0.2562397316514976,"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."}}