{"id":"W3197559989","doi":"","title":"An n-gram Approach to Exploiting a Monolingual Corpus for Machine Translation","year":2005,"lang":"en","type":"article","venue":"O2 - Repositori Institucional (Universitat Oberta de Catalunya)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; n-gram; Computer science; Natural language processing; Translation (biology); Artificial intelligence; Linguistics; Language model","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002859918,0.0002493089,0.000219239,0.0003007855,0.0005052708,0.000245182,0.001198932,0.0001612635,0.00000173341],"category_scores_gemma":[0.00005971944,0.0002739992,0.0001163506,0.0005280137,0.00003717032,0.002012193,0.0001321014,0.0002314975,0.000006636682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003525167,"about_ca_system_score_gemma":0.0001945292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001653676,"about_ca_topic_score_gemma":0.0000808634,"domain_scores_codex":[0.9982026,0.00004839908,0.0002377698,0.0006923312,0.0003903166,0.0004286073],"domain_scores_gemma":[0.9987134,0.000101893,0.000134782,0.0005271239,0.0002302795,0.0002925661],"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":[0.0003932956,0.0009907904,0.0004496766,0.0001935184,0.0001398558,0.0001605859,0.02474661,0.004987796,0.1177551,0.4103732,0.00132811,0.4384815],"study_design_scores_gemma":[0.002658321,0.0009580782,0.0002457291,0.0002464235,0.0001616348,0.001256856,0.001058509,0.8394702,0.09256864,0.008395563,0.05086547,0.002114552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02623857,0.0009388434,0.968044,0.0009286701,0.0003530958,0.0005096049,0.00002366036,0.0006696553,0.00229391],"genre_scores_gemma":[0.4841371,0.000002489254,0.5151576,0.0001481659,0.000295761,0.00002274214,0.00009386738,0.00001534173,0.0001268817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8344824,"threshold_uncertainty_score":0.9999712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01886890441132595,"score_gpt":0.2686632120982062,"score_spread":0.2497943076868803,"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."}}