{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"918e7084900e","filters":{"venue":"Natural language processing"}},"results":[{"id":"W2548230849","doi":"10.1075/nlp.2.15mey","title":"Extracting knowledge-rich contexts for terminography","year":2001,"lang":"en","type":"book-chapter","venue":"Natural language processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":215,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Construct (python library); Computer science; Paralanguage; Domain knowledge; Domain (mathematical analysis); Knowledge extraction; Field (mathematics); Context (archaeology); Knowledge management; Natural language processing; Data science; Artificial intelligence; Psychology; Communication; Geography; Mathematics","authors":[{"name":"Ingrid Meyer","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01563003246822913,"gpt":0.3028685290154244,"spread":0.2872384965471953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001388135,0.0006908762,0.0005911522,0.00303333,0.001131591,0.002879164,0.00116295,0.0007922247,0.004759598],"category_scores_gemma":[0.005998624,0.0007256229,0.000913582,0.003312267,0.001411841,0.0072093,0.002355797,0.001868099,0.003611285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000786385,"about_ca_system_score_gemma":0.001068362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005800364,"about_ca_topic_score_gemma":0.001760938,"domain_scores_codex":[0.9990559,0.0003599697,0.00009406748,0.000157749,0.0002960226,0.00003618616],"domain_scores_gemma":[0.9973213,0.001852538,0.00009813302,0.00042182,0.0002590098,0.00004717746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006190898,0.00003753115,0.001043282,0.001316286,0.00004172568,0.0006070177,0.003521673,0.003542223,0.0102667,0.4065999,0.02007541,0.5528864],"study_design_scores_gemma":[0.00002108273,0.00003236941,0.001284014,0.001198116,0.00007026547,0.001368206,0.00097531,0.02688494,0.01558705,0.5650083,0.3875002,0.00007004268],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006694648,0.005613583,0.9614586,0.000645461,0.0002187884,0.0001626671,0.0004666967,0.001202827,0.02353679],"genre_scores_gemma":[0.03957,0.005195871,0.9443949,0.0001824101,0.0001314663,0.0002233798,0.001525029,0.0004938144,0.008283064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004759598,"threshold_uncertainty_score":0.01592249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2475426007","doi":"10.1075/nlp.9.05hab","title":"Arabic preprocessing for Statistical Machine Translation","year":2012,"lang":"en","type":"book-chapter","venue":"Natural language processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Arabic; Preprocessor; Computer science; Natural language processing; Translation (biology); Machine translation; Artificial intelligence; Linguistics; Philosophy; Chemistry","authors":[{"name":"Nizar Habash","is_ca":false},{"name":"Fatiha Sadat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01989698859571343,"gpt":0.2977855957314866,"spread":0.2778886071357731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007088049,0.001939169,0.0006932975,0.002085289,0.0008792074,0.002480102,0.000909023,0.0009274623,0.05609729],"category_scores_gemma":[0.002509505,0.0005148371,0.0006317418,0.004076818,0.0005829395,0.002039711,0.001071717,0.00208894,0.05844421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007461538,"about_ca_system_score_gemma":0.0008219837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000580272,"about_ca_topic_score_gemma":0.0009912975,"domain_scores_codex":[0.9992717,0.0001589656,0.00005679534,0.0001300971,0.0003583518,0.00002416978],"domain_scores_gemma":[0.9990278,0.00039515,0.00005238973,0.0002164297,0.0002797338,0.00002847638],"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":[0.00005313639,0.00004119166,0.0001635437,0.0008354168,0.00002926254,0.0002314832,0.0002055147,0.002020884,0.012822,0.05545748,0.1394169,0.7887232],"study_design_scores_gemma":[0.000008660308,0.00004487879,0.0004376755,0.0002818006,0.00001696523,0.0008856605,0.00006760712,0.008333332,0.01193517,0.04027269,0.9376802,0.00003526243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003210475,0.04136722,0.6817011,0.00276356,0.004012957,0.0003132169,0.001595624,0.01123346,0.2538023],"genre_scores_gemma":[0.03051479,0.03346782,0.7141019,0.001585932,0.002231833,0.0005309599,0.004412454,0.004429098,0.2087253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05609729,"threshold_uncertainty_score":0.1876641,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}