{"id":"W2890620592","doi":"10.18653/v1/w18-5805","title":"String Transduction with Target Language Models and Insertion Handling","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; University of Alberta","keywords":"Transduction (biophysics); Grapheme; Computer science; String (physics); Natural language processing; Sequence (biology); Word (group theory); Projection (relational algebra); Artificial intelligence; Syllabification; Inflection; Language model; Speech recognition; Linguistics; Algorithm; Biology; Mathematics; Syllable; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001773819,0.001563583,0.001029584,0.001166157,0.0005996047,0.002603939,0.002512783,0.001832942,0.01149132],"category_scores_gemma":[0.006710083,0.0009912031,0.001631545,0.001676577,0.001351822,0.006282211,0.00383943,0.003901258,0.01236519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005365619,"about_ca_system_score_gemma":0.0009449666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007445886,"about_ca_topic_score_gemma":0.001062306,"domain_scores_codex":[0.9978854,0.000626954,0.0001822462,0.0006657391,0.0004942781,0.0001453233],"domain_scores_gemma":[0.9971973,0.001111421,0.0001467521,0.0009875511,0.0004898849,0.00006704673],"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":[0.000725103,0.0004393205,0.002762744,0.001008993,0.0002100857,0.001533502,0.001274544,0.1542185,0.09117366,0.153613,0.02695036,0.5660902],"study_design_scores_gemma":[0.00002779885,0.0001251449,0.0003529913,0.00003571983,0.00005162759,0.0005464676,0.0001470784,0.7595673,0.05654448,0.1670284,0.01551088,0.00006212071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01436957,0.0001338531,0.9642845,0.0002925819,0.0001476017,0.00006353891,0.0007756567,0.01613206,0.00380057],"genre_scores_gemma":[0.4702257,0.0004622295,0.4996754,0.0005806906,0.0002811227,0.0003019709,0.008084153,0.006846297,0.01354239],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01149132,"threshold_uncertainty_score":0.03844231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01708827348458499,"score_gpt":0.2616792634933338,"score_spread":0.2445909900087488,"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."}}