{"id":"W4245584151","doi":"10.1145/564437.564438","title":"Using self-supervised word segmentation in Chinese information retrieval","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Character (mathematics); Word (group theory); Text segmentation; Natural language processing; Segmentation; Pattern recognition (psychology)","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":[0.001301226,0.0002358227,0.0002274276,0.00154875,0.0002216414,0.0007521277,0.00192874,0.000171137,0.00007671304],"category_scores_gemma":[0.001921879,0.0001858488,0.00004025486,0.001822111,0.0001523013,0.00794639,0.0009278784,0.0005530443,0.00006235315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004515912,"about_ca_system_score_gemma":0.0001929405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002230122,"about_ca_topic_score_gemma":0.0000032857,"domain_scores_codex":[0.9965603,0.00002947244,0.001031915,0.0002686372,0.001683223,0.0004265049],"domain_scores_gemma":[0.9974813,0.000181772,0.0004453569,0.0002427836,0.00154755,0.0001012331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002261668,0.001755657,0.2520891,0.0009855743,0.0002271975,0.000004812898,0.09463584,0.0003932595,0.008719482,0.4273816,0.004664174,0.2068816],"study_design_scores_gemma":[0.009402172,0.00115789,0.2741214,0.001275886,0.000009326386,0.0000442864,0.01979029,0.5351332,0.09578827,0.05098338,0.01048365,0.00181014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873,0.00002610304,0.001360447,0.003484472,0.0003356652,0.0009136508,0.0000236857,0.0001597313,0.006396198],"genre_scores_gemma":[0.9817844,0.0001998213,0.01764981,0.0001674141,0.0000193788,0.00003254889,0.00001956539,0.000005540405,0.0001215134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.53474,"threshold_uncertainty_score":0.7578695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08421405815381645,"score_gpt":0.335416479760529,"score_spread":0.2512024216067126,"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."}}