{"id":"W1999646438","doi":"10.1075/term.10.1.07lan","title":"General-purpose statistical translation engine and domain specific texts","year":2004,"lang":"en","type":"article","venue":"Terminology International Journal of Theoretical and Applied Issues in Specialized Communication","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Terminology; Computer science; Machine translation; Natural language processing; Word error rate; Word (group theory); Artificial intelligence; Field (mathematics); Domain (mathematical analysis); Information retrieval; Linguistics; Mathematics","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":[0.0004681335,0.0001219186,0.0002384434,0.0002322051,0.00004957883,0.0001123664,0.0009096436,0.0001096021,0.00003967189],"category_scores_gemma":[0.00003804748,0.0001028295,0.00002592936,0.00009578537,0.0005412916,0.0002382156,0.0002329346,0.0003346167,0.00000197424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006654819,"about_ca_system_score_gemma":0.00002397573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004203709,"about_ca_topic_score_gemma":0.000002311901,"domain_scores_codex":[0.9988885,0.000106914,0.0004630846,0.0001677783,0.0002409041,0.0001328191],"domain_scores_gemma":[0.9992366,0.0001929164,0.0001814877,0.0002317741,0.000101086,0.00005617833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001016174,0.00006120808,0.0000171633,0.000003067743,0.00001190276,0.00002545557,0.0008009917,0.00000474358,0.004215632,0.8746966,0.00002291219,0.1200388],"study_design_scores_gemma":[0.001295794,0.00006814893,0.0003914289,0.00005633851,0.00000563855,0.0002738283,0.00003210504,0.0001390961,0.009419421,0.9851058,0.00309968,0.0001126991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1657919,0.009548362,0.8001187,0.02169166,0.0002585037,0.0002508717,0.000006081976,0.0000858503,0.002248046],"genre_scores_gemma":[0.5345962,0.001533042,0.4636411,0.000128063,0.00008516427,0.000003560186,0.000004865935,0.000004403694,0.000003529896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3688043,"threshold_uncertainty_score":0.4193265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01148244170581296,"score_gpt":0.3026671055725336,"score_spread":0.2911846638667206,"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."}}