{"id":"W2250317589","doi":"10.63317/5oexzp4sjvme","title":"Improving Entity Linking using Surface Form Refinement","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Polytechnique Montréal","funders":"","keywords":"Entity linking; Computer science; Rewriting; Natural language processing; Context (archaeology); NIST; Annotation; Task (project management); Word (group theory); Matching (statistics); Information retrieval; Artificial intelligence; Knowledge base; Similarity (geometry); Process (computing); Named entity; Linguistics; Programming language; Mathematics","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":[0.008449505,0.002000685,0.002512142,0.007363246,0.001757129,0.005940692,0.003442613,0.002612259,0.01408171],"category_scores_gemma":[0.06307871,0.001378918,0.003846421,0.009613791,0.001226741,0.009995803,0.00916355,0.003405353,0.006962055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007810948,"about_ca_system_score_gemma":0.002687873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005737483,"about_ca_topic_score_gemma":0.007417833,"domain_scores_codex":[0.9882172,0.003098102,0.001591566,0.002000409,0.004551185,0.000541633],"domain_scores_gemma":[0.9599401,0.01311655,0.00168601,0.01546225,0.00941959,0.0003754141],"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":[0.000354084,0.0003518562,0.0139858,0.0007721086,0.0003112517,0.0004946165,0.00108967,0.04232145,0.01470287,0.03698809,0.03347785,0.8551503],"study_design_scores_gemma":[0.0001075737,0.0002045388,0.00357767,0.0002164873,0.0004132567,0.000691084,0.001087425,0.7862383,0.04566118,0.1038452,0.0578342,0.0001232097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01032471,0.000243146,0.9759444,0.0003417789,0.0001513128,0.0002403692,0.0009423498,0.009613407,0.002198522],"genre_scores_gemma":[0.1001014,0.0003267503,0.88684,0.0002370174,0.00007508868,0.0001597312,0.006116931,0.002525378,0.003617654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01408171,"threshold_uncertainty_score":0.04710805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2097279930675458,"score_gpt":0.4123134049304373,"score_spread":0.2025854118628914,"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."}}