{"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/incorporating-discrete-translation-lexicons","title":"Incorporating Discrete Translation Lexicons into Neural Machine Translation","arxiv_id":"1606.02006","date":"2016-06-07","proceeding":"EMNLP 2016 11","authors":["Philip Arthur","Graham Neubig","Satoshi Nakamura"],"abstract":"Neural machine translation (NMT) often makes mistakes in translating\nlow-frequency content words that are essential to understanding the meaning of\nthe sentence. We propose a method to alleviate this problem by augmenting NMT\nsystems with discrete translation lexicons that efficiently encode translations\nof these low-frequency words. We describe a method to calculate the lexicon\nprobability of the next word in the translation candidate by using the\nattention vector of the NMT model to select which source word lexical\nprobabilities the model should focus on. We test two methods to combine this\nprobability with the standard NMT probability: (1) using it as a bias, and (2)\nlinear interpolation. Experiments on two corpora show an improvement of 2.0-2.3\nBLEU and 0.13-0.44 NIST score, and faster convergence time.","url_abs":"http://arxiv.org/abs/1606.02006v2","url_pdf":"http://arxiv.org/pdf/1606.02006v2.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":"incorporating-discrete-translation-lexicons","repo_url":"https://github.com/duyvuleo/Transformer-DyNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"incorporating-discrete-translation-lexicons","repo_url":"https://github.com/tnq177/improving_lexical_choice_in_nmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1606.02006","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}