{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T14:09:43Z","timestamp":1776348583771,"version":"3.51.2"},"reference-count":2,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2017,12]]},"abstract":"<jats:p> Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a subword-level encoder on WMT\u201915 DE-EN and CS-EN, and gives comparable performance on FI-EN and RU-EN. We then demonstrate that it is possible to share a single character-level encoder across multiple languages by training a model on a many-to-one translation task. In this multilingual setting, the character-level encoder significantly outperforms the subword-level encoder on all the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of the BLEU score and human judgment. <\/jats:p>","DOI":"10.1162\/tacl_a_00067","type":"journal-article","created":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T15:42:50Z","timestamp":1546011770000},"page":"365-378","source":"Crossref","is-referenced-by-count":136,"title":["Fully Character-Level Neural Machine Translation without Explicit                     Segmentation"],"prefix":"10.1162","volume":"5","author":[{"given":"Jason","family":"Lee","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich,"}]},{"given":"Kyunghyun","family":"Cho","sequence":"additional","affiliation":[{"name":"New York University,"}]},{"given":"Thomas","family":"Hofmann","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich,"}]}],"member":"281","reference":[{"issue":"1","key":"p_12","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1017\/S1351324915000339","volume":"23","author":"Graham Yvette","year":"2017","journal-title":"Natural Language Engineering"},{"key":"p_13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/tacl_a_00067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:13Z","timestamp":1615585093000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":2,"alternative-id":["10.1162\/tacl_a_00067"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00067","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}