{"id":"W4386427483","doi":"10.1016/j.softx.2023.101508","title":"CoTranslate: A web-based tool for crowdsourcing high-quality sentence pair corpora","year":2023,"lang":"en","type":"article","venue":"SoftwareX","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Crowdsourcing; Computer science; Sentence; World Wide Web; Natural language processing; Quality (philosophy); Web application; Artificial intelligence","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":[0.001011321,0.0002027674,0.0002453146,0.0001656826,0.0002241591,0.0002136312,0.001055371,0.0001245527,0.00001163663],"category_scores_gemma":[0.0004718302,0.0001863306,0.0001300869,0.0009173607,0.00007857435,0.0003865869,0.0001593718,0.0001925684,0.00004760669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000563781,"about_ca_system_score_gemma":0.0002111941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007058521,"about_ca_topic_score_gemma":0.000008461708,"domain_scores_codex":[0.9981728,0.00008104243,0.0003270238,0.0005595681,0.0003852935,0.000474245],"domain_scores_gemma":[0.9983041,0.0006016262,0.0001580081,0.0006552574,0.0001997431,0.00008124057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002927069,0.0003447338,0.03780948,0.002451344,0.0001208815,0.0004357814,0.002470082,0.000814554,0.1284283,0.101596,0.0625362,0.6626999],"study_design_scores_gemma":[0.004722599,0.0005343689,0.01220492,0.000838103,0.00005793711,0.00003654556,0.00005736028,0.1733399,0.3189166,0.4731058,0.01345103,0.002734864],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04541855,0.0002248198,0.9447135,0.002262519,0.0002937926,0.0003984195,0.00004060859,0.006638503,0.000009311217],"genre_scores_gemma":[0.5554218,0.000001650803,0.4435721,0.0006849432,0.00004363135,0.00008013707,0.00002465765,0.00001827979,0.0001526999],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.659965,"threshold_uncertainty_score":0.759834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02795925307258903,"score_gpt":0.3009481217690872,"score_spread":0.2729888686964982,"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."}}