[2011.02121] PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2011.02121 (cs) [Submitted on 4 Nov 2020] Title: PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents Authors: Ryo Fujii , Masato Mita , Kaori Abe , Kazuaki Hanawa , Makoto Morishita , Jun Suzuki , Kentaro Inui View a PDF of the paper titled PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents, by Ryo Fujii and 5 other authors View PDF HTML (experimental) Abstract: Neural Machine Translation (NMT) has shown drastic improvement in its quality when translating clean input, such as text from the news domain. However, existing studies suggest that NMT still struggles with certain kinds of input with considerable noise, such as User-Generated Contents (UGC) on the Internet. To make better use of NMT for cross-cultural communication, one of the most promising directions is to develop a model that correctly handles these expressions. Though its importance has been recognized, it is still not clear as to what creates the great gap in performance between the translation of clean input and that of UGC. To answer the question, we present a new dataset, PheMT, for evaluating the robustness of MT systems against specific linguistic phenomena in Japanese-English translation. Our experiments with the created dataset revealed that not only our in-house models but even widely used off-the-shelf systems are greatly disturbed by the presence of certain phenomena. Comments: 15 pages, 4 figures, accepted at COLING 2020 Subjects: Computation and Language (cs.CL) Cite as: arXiv:2011.02121 [cs.CL] (or arXiv:2011.02121v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2011.02121 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the 28th International Conference on Computational Linguistics, pages 5929-5943, 2020 Related DOI : https://doi.org/10.18653/v1/2020.coling-main.521 Focus to learn more DOI(s) linking to related resources Submission history From: Ryo Fujii [ view email ] [v1] Wed, 4 Nov 2020 04:44:47 UTC (1,095 KB) Full-text links: Access Paper: View a PDF of the paper titled PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents, by Ryo Fujii and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2020-11 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar DBLP - CS Bibliography listing | bibtex Masato Mita Kaori Abe Kazuaki Hanawa Makoto Morishita Jun Suzuki … export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from