{"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/a-multifaceted-evaluation-of-neural-versus","title":"A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions","arxiv_id":"1701.02901","date":"2017-01-11","proceeding":"EACL 2017 4","authors":["Antonio Toral","Víctor M. Sánchez-Cartagena"],"abstract":"We aim to shed light on the strengths and weaknesses of the newly introduced\nneural machine translation paradigm. To that end, we conduct a multifaceted\nevaluation in which we compare outputs produced by state-of-the-art neural\nmachine translation and phrase-based machine translation systems for 9 language\ndirections across a number of dimensions. Specifically, we measure the\nsimilarity of the outputs, their fluency and amount of reordering, the effect\nof sentence length and performance across different error categories. We find\nout that translations produced by neural machine translation systems are\nconsiderably different, more fluent and more accurate in terms of word order\ncompared to those produced by phrase-based systems. Neural machine translation\nsystems are also more accurate at producing inflected forms, but they perform\npoorly when translating very long sentences.","url_abs":"http://arxiv.org/abs/1701.02901v1","url_pdf":"http://arxiv.org/pdf/1701.02901v1.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":"a-multifaceted-evaluation-of-neural-versus","repo_url":"https://github.com/antot/neural_vs_-phrasebased_smt_eacl17","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1701.02901","atlas_url":"https://app.syntology.ai/?focus=1701.02901","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}