{"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/factored-neural-machine-translation","title":"Factored Neural Machine Translation","arxiv_id":"1609.04621","date":"2016-09-15","proceeding":null,"authors":["Mercedes García-Martínez","Loïc Barrault","Fethi Bougares"],"abstract":"We present a new approach for neural machine translation (NMT) using the\nmorphological and grammatical decomposition of the words (factors) in the\noutput side of the neural network. This architecture addresses two main\nproblems occurring in MT, namely dealing with a large target language\nvocabulary and the out of vocabulary (OOV) words. By the means of factors, we\nare able to handle larger vocabulary and reduce the training time (for systems\nwith equivalent target language vocabulary size). In addition, we can produce\nnew words that are not in the vocabulary. We use a morphological analyser to\nget a factored representation of each word (lemmas, Part of Speech tag, tense,\nperson, gender and number). We have extended the NMT approach with attention\nmechanism in order to have two different outputs, one for the lemmas and the\nother for the rest of the factors. The final translation is built using some\n\\textit{a priori} linguistic information. We compare our extension with a\nword-based NMT system. The experiments, performed on the IWSLT'15 dataset\ntranslating from English to French, show that while the performance do not\nalways increase, the system can manage a much larger vocabulary and\nconsistently reduce the OOV rate. We observe up to 2% BLEU point improvement in\na simulated out of domain translation setup.","url_abs":"http://arxiv.org/abs/1609.04621v1","url_pdf":"http://arxiv.org/pdf/1609.04621v1.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":"factored-neural-machine-translation","repo_url":"https://github.com/lium-lst/nmtpy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}