{"id":"W49270455","doi":"","title":"Using Unigram and Bigram Language Models for Monolingual and Cross-Language IR","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bigram; Computer science; Natural language processing; Artificial intelligence; Word (group theory); Search engine indexing; Machine translation; Cross-language information retrieval; Translation (biology); Character (mathematics); Speech recognition; Linguistics; Mathematics; Trigram","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":[0.000612358,0.0001824753,0.0001777517,0.0001979515,0.0001738374,0.0004346054,0.0003922679,0.0001307829,0.000001675716],"category_scores_gemma":[0.00007729567,0.0001529975,0.00003702341,0.0002650261,0.00009866773,0.0007307256,0.000296669,0.0001447937,3.668752e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012489,"about_ca_system_score_gemma":0.00003399855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004129075,"about_ca_topic_score_gemma":0.00009833384,"domain_scores_codex":[0.9987602,0.00001540574,0.0002214472,0.0004402998,0.0001623733,0.0004003322],"domain_scores_gemma":[0.9992354,0.0001391619,0.00007753535,0.0003327482,0.00008796685,0.0001272251],"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":[0.00007352096,0.00009844371,0.0007370946,0.0002573482,0.00004107808,0.0002081057,0.0273487,0.00008481032,0.1092154,0.1806176,0.0001029585,0.6812149],"study_design_scores_gemma":[0.0009470764,0.0001759984,0.0002108477,0.00008235847,0.00002048401,0.0002775427,0.0009539339,0.6840834,0.2418892,0.07049562,0.0001257157,0.0007378341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.356268,0.004362018,0.638399,0.0000373217,0.00004171354,0.0001819239,0.000003124217,0.0004839803,0.0002229399],"genre_scores_gemma":[0.5069334,0.000007227586,0.4926725,0.0001931354,0.0000430565,0.00000305234,0.000001503115,0.0000104288,0.0001356627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6839986,"threshold_uncertainty_score":0.6239059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03112713027741485,"score_gpt":0.3634326685443653,"score_spread":0.3323055382669505,"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."}}