{"id":"W2967423807","doi":"","title":"Lemmatising Treebanks. Corpus Annotation with Knowledge Bases","year":2018,"lang":"es","type":"article","venue":"RAEL: revista electrónica de lingüística aplicada","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Treebank; Annotation; Artificial intelligence; Parsing; Natural language processing; Humanities; Linguistics; Computer science; Corpus linguistics; Art; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005838912,0.0007722558,0.000893105,0.0003389264,0.001881857,0.001974986,0.0005127557,0.0002147983,0.0009041842],"category_scores_gemma":[0.0004713015,0.0006384647,0.0003168724,0.0005020336,0.001716039,0.0003360743,0.0001375789,0.0006942748,0.0002773718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001746953,"about_ca_system_score_gemma":0.00038988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000345371,"about_ca_topic_score_gemma":0.0007081294,"domain_scores_codex":[0.9960796,0.0003354315,0.0008642146,0.0009793793,0.0004501237,0.001291242],"domain_scores_gemma":[0.9966604,0.0009458707,0.0005095838,0.0008264455,0.0007559519,0.000301717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00086656,0.0008480689,0.002419442,0.001524291,0.001149406,0.0001168369,0.02949597,0.00000286625,0.001776206,0.8894244,0.01675537,0.05562058],"study_design_scores_gemma":[0.001250723,0.002379158,0.001643069,0.002300132,0.001030412,0.00007231562,0.001314472,0.0008964037,0.002030444,0.0008757267,0.9849476,0.001259563],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6444206,0.07510822,0.00695047,0.002643985,0.0009005422,0.002695283,0.000547805,0.001470981,0.2652621],"genre_scores_gemma":[0.9901881,0.001078191,0.001049077,0.0007597646,0.004010755,0.0000886786,0.00007199346,0.0001532417,0.002600266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9681922,"threshold_uncertainty_score":0.9996067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01399181277315071,"score_gpt":0.2642212846142912,"score_spread":0.2502294718411405,"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."}}