{"id":"W4312215389","doi":"10.5334/johd.94","title":"The TRANSCOMP Dataset of Literary Translations from 120 Languages and a Parallel Collection of English-language Originals","year":2022,"lang":"en","type":"article","venue":"Journal of Open Humanities Data","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Linguistics; Computer science; Word (group theory); Metadata; Literary translation; Natural language processing; Literature; History; Art; World Wide Web; Philosophy","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":[0.0009834499,0.00009134463,0.0002428509,0.0001270463,0.0003217241,0.0003718863,0.004125839,0.00001966848,0.00008256155],"category_scores_gemma":[0.0001063407,0.00006684343,0.00003268147,0.0002032514,0.00009805195,0.002081309,0.000981051,0.0002728752,8.67767e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022096,"about_ca_system_score_gemma":0.0001317631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004489318,"about_ca_topic_score_gemma":0.0001479819,"domain_scores_codex":[0.9986591,0.0002186719,0.0005098041,0.0001621051,0.0003508145,0.00009954373],"domain_scores_gemma":[0.9981995,0.0003571958,0.0005433396,0.0007226967,0.0001511835,0.00002610049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001535719,0.001192455,0.001178418,0.0004791016,0.001288309,0.0004620322,0.4465984,0.00009943378,0.01593212,0.09410277,0.3038163,0.133315],"study_design_scores_gemma":[0.007027684,0.003077257,0.001187815,0.001033169,0.0006511596,0.0005451445,0.0622686,0.01101246,0.02120046,0.08971287,0.8008808,0.001402567],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.241362,0.3859849,0.2463008,0.005111989,0.003205418,0.003408234,0.1109564,0.0002950977,0.003375209],"genre_scores_gemma":[0.665126,0.0007841489,0.3312152,0.0002821283,0.0002673559,0.00001996347,0.002039879,0.00002355029,0.000241739],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4970645,"threshold_uncertainty_score":0.7666903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05700619531125964,"score_gpt":0.3531706120189455,"score_spread":0.2961644167076859,"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."}}