{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/diabla-a-corpus-of-bilingual-spontaneous","title":"DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation","arxiv_id":"1905.13354","date":"2019-05-30","proceeding":null,"authors":["Rachel Bawden","Sophie Rosset","Thomas Lavergne","Eric Bilinski"],"abstract":"We present a new English-French test set for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. The test set contains 144 spontaneous dialogues (5,700+ sentences) between native English and French speakers, mediated by one of two neural MT systems in a range of role-play settings. The dialogues are accompanied by fine-grained sentence-level judgments of MT quality, produced by the dialogue participants themselves, as well as by manually normalised versions and reference translations produced a posteriori. The motivation for the corpus is two-fold: to provide (i) a unique resource for evaluating MT models, and (ii) a corpus for the analysis of MT-mediated communication. We provide a preliminary analysis of the corpus to confirm that the participants' judgments reveal perceptible differences in MT quality between the two MT systems used.","url_abs":"https://arxiv.org/abs/1905.13354v1","url_pdf":"https://arxiv.org/pdf/1905.13354v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"diabla-a-corpus-of-bilingual-spontaneous","repo_url":"https://github.com/rbawden/DiaBLa-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"diabla-a-corpus-of-bilingual-spontaneous","repo_url":"https://github.com/rbawden/diabla-chat-interface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[{"slug":"diabla","name":"DiaBLa","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.13354","atlas_url":"https://app.syntology.ai/?focus=1905.13354","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}