{"id":"W2167907745","doi":"10.1109/rcis.2011.6006865","title":"Extracting the multilingual terminology from a web-based encyclopedia","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Terminology; Encyclopedia; Rank (graph theory); Natural language processing; Information retrieval; Exploit; Artificial intelligence; Term (time); Filter (signal processing); World Wide Web; Linguistics; Library science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007024066,0.001318143,0.001054137,0.01682571,0.001085805,0.002542441,0.0008071228,0.0005398309,0.005922928],"category_scores_gemma":[0.00477401,0.000446139,0.001044705,0.01277766,0.0005060401,0.003163643,0.001807192,0.0007789514,0.005110445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000731867,"about_ca_system_score_gemma":0.002434469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003140188,"about_ca_topic_score_gemma":0.005761028,"domain_scores_codex":[0.9991655,0.0001202116,0.0002297349,0.0002324915,0.0001862046,0.00006590288],"domain_scores_gemma":[0.9980918,0.0006598977,0.0002108177,0.0001938495,0.0007474676,0.00009619272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000358234,0.0002325216,0.01162189,0.006815078,0.000329997,0.004507824,0.003472178,0.00281308,0.1568483,0.02135691,0.02898722,0.7626567],"study_design_scores_gemma":[0.0001621534,0.0008540282,0.0668779,0.002413491,0.001666887,0.01100987,0.01475307,0.03923997,0.1390297,0.02293279,0.7005848,0.0004754707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3100771,0.0115756,0.5241128,0.002047608,0.0009311048,0.002254553,0.07367563,0.009564707,0.06576091],"genre_scores_gemma":[0.2513137,0.004984304,0.6400761,0.0002691976,0.0002685764,0.001020543,0.09269117,0.001329024,0.008047447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01682571,"threshold_uncertainty_score":0.01981413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03085400693688622,"score_gpt":0.2778228173745137,"score_spread":0.2469688104376275,"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."}}