{"id":"W7100328590","doi":"","title":"The Use of Approximate String Matching Techniques in the Alignment of Sentences in Parallel Corpora Abstract","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Lexicon; Task (project management); Parallel corpora; Terminology; Matching (statistics); String (physics); Similarity (geometry)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00404757,0.000555111,0.0009082763,0.004424921,0.001314377,0.002639772,0.001588043,0.001277699,0.003552552],"category_scores_gemma":[0.02763077,0.000557732,0.0005422235,0.00965272,0.001310779,0.005465061,0.002141296,0.001081303,0.002906796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006972223,"about_ca_system_score_gemma":0.001192728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001875863,"about_ca_topic_score_gemma":0.002326773,"domain_scores_codex":[0.9943699,0.002968219,0.0005550165,0.0009341106,0.001010711,0.0001621467],"domain_scores_gemma":[0.9885284,0.00716262,0.001007387,0.001724171,0.001464678,0.00011263],"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":[0.0006672682,0.0001768886,0.004812672,0.0006681705,0.0001486042,0.0008086425,0.00173517,0.03414351,0.03682277,0.04920599,0.006245851,0.8645645],"study_design_scores_gemma":[0.0001252566,0.000441176,0.007084112,0.0001630339,0.0002034488,0.001664834,0.001737778,0.7700178,0.06203701,0.1185514,0.03786076,0.0001134499],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04344424,0.0007643803,0.9496068,0.0002956404,0.0001053969,0.000176814,0.000480113,0.001841045,0.003285625],"genre_scores_gemma":[0.1470897,0.0004505701,0.8490657,0.00008863355,0.00009548923,0.0001575987,0.001482202,0.0003022369,0.001267921],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004424921,"threshold_uncertainty_score":0.02140588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05586752220573239,"score_gpt":0.2785768931160343,"score_spread":0.222709370910302,"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."}}