{"id":"W2579759882","doi":"10.63317/47iyyzyji28j","title":"SemLinker, a Modular and Open Source Framework for Named Entity Discovery and Linking","year":2016,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Polytechnique Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Entity linking; Annotation; Knowledge base; Information retrieval; Modular design; Named-entity recognition; Cluster analysis; Named entity; Open source; Population; World Wide Web; Natural language processing; Artificial intelligence; Programming language; Software; Engineering; Task (project management)","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":[0.004406227,0.001874686,0.001567248,0.006833217,0.00177702,0.005416815,0.00444464,0.002022439,0.02677997],"category_scores_gemma":[0.01367062,0.001824457,0.002919749,0.004575938,0.00111159,0.008522335,0.007179339,0.003894601,0.01885401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001007288,"about_ca_system_score_gemma":0.003408542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003881752,"about_ca_topic_score_gemma":0.008532386,"domain_scores_codex":[0.9973151,0.000456599,0.0002891129,0.0007401191,0.001057047,0.0001419359],"domain_scores_gemma":[0.9951453,0.002175909,0.0003571374,0.001434031,0.0006235999,0.0002638926],"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":[0.000723091,0.0005426017,0.003107532,0.002627166,0.0009342555,0.001095617,0.001362216,0.009522098,0.01807088,0.0885639,0.2782315,0.5952193],"study_design_scores_gemma":[0.0002264872,0.0001227567,0.002023786,0.000430454,0.0003338338,0.001348602,0.0003977474,0.1418407,0.03833982,0.1752463,0.6393432,0.0003463059],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001166466,0.0002714312,0.8141192,0.0002497177,0.0002180837,0.0002816235,0.005902968,0.1738432,0.00394729],"genre_scores_gemma":[0.02082983,0.0007602611,0.8998486,0.0005317865,0.0001654358,0.0005647917,0.0385398,0.02449623,0.01426335],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02677997,"threshold_uncertainty_score":0.08958793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01630154427553545,"score_gpt":0.2924813700318744,"score_spread":0.2761798257563389,"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."}}