{"id":"W4384405916","doi":"10.1145/3606699","title":"Comparing Heuristic Rules and Masked Language Models for Entity Alignment in the Literature Domain","year":2023,"lang":"en","type":"article","venue":"Journal on Computing and Cultural Heritage","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Heuristics; Computer science; Heuristic; Variety (cybernetics); Identifier; Metadata; Set (abstract data type); Preprocessor; Domain (mathematical analysis); Information retrieval; Tree (set theory); Natural language processing; Data science; Data mining; Artificial intelligence; World Wide Web; Programming language","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":[0.0006829876,0.0001153253,0.0001692462,0.00005568986,0.0003207118,0.0007179698,0.0002972792,0.00003922774,2.715059e-7],"category_scores_gemma":[0.00003028015,0.00006551015,0.00004712781,0.000160966,0.0000292433,0.0002187247,0.0001143988,0.0002282674,0.00000146717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001884828,"about_ca_system_score_gemma":0.00000674945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008710714,"about_ca_topic_score_gemma":0.00001037922,"domain_scores_codex":[0.9990982,0.0001026338,0.0001860684,0.0001858554,0.0001661851,0.0002610771],"domain_scores_gemma":[0.9995346,0.0002096759,0.00007180651,0.0001126884,0.00002606566,0.00004518365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002149395,0.0004076834,0.01301899,0.0007856336,0.0001979485,0.00306607,0.4419071,0.009568932,0.002537873,0.4162916,0.009195358,0.1028079],"study_design_scores_gemma":[0.002630246,0.0004628486,0.08230351,0.001120162,0.00002119634,0.001515114,0.03722152,0.7760081,0.00007237673,0.09641495,0.001631035,0.0005989468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873064,0.0009281458,0.01001705,0.001213823,0.0001978863,0.0001175212,0.000001814839,0.00006001834,0.000157346],"genre_scores_gemma":[0.9949071,0.0001142893,0.004519694,0.0002817505,0.0001170604,0.000002386415,0.000002808126,0.000003530441,0.00005133294],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7664391,"threshold_uncertainty_score":0.69234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03274933385203833,"score_gpt":0.2888449563192416,"score_spread":0.2560956224672032,"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."}}