{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:08:51Z","timestamp":1774872531757,"version":"3.50.1"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T00:00:00Z","timestamp":1563840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61525205, 61751206, 61876120"],"award-info":[{"award-number":["61525205, 61751206, 61876120"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2020,1,31]]},"abstract":"<jats:p>\n            In this article, we show that word translations can be explicitly incorporated into NMT effectively to avoid wrong translations. Specifically, we propose three cross-lingual encoders to explicitly incorporate word translations into NMT: (1)\n            <jats:italic>Factored<\/jats:italic>\n            encoder, which encodes a word and its translation in a vertical way; (2)\n            <jats:italic>Gated<\/jats:italic>\n            encoder, which uses a gated mechanism to selectively control the amount of word translations moving forward; and (3)\n            <jats:italic>Mixed<\/jats:italic>\n            encoder, which stitchingly learns a word and its translation annotations over sequences where words and their translations are alternatively mixed. Besides, we first use a simple word dictionary approach and then a word sense disambiguation (WSD) approach to effectively model the word context for better word translation. Experimentation on Chinese-to-English translation demonstrates that all proposed encoders are able to improve the translation accuracy for both traditional RNN-based NMT and recent self-attention-based NMT (hereafter referred to as\n            <jats:italic>Transformer<\/jats:italic>\n            ). Specifically,\n            <jats:italic>Mixed<\/jats:italic>\n            encoder yields the most significant improvement of 2.0 in BLEU on the RNN-based NMT, while\n            <jats:italic>Gated<\/jats:italic>\n            encoder improves 1.2 in BLEU on\n            <jats:italic>Transformer<\/jats:italic>\n            . This indicates the usefulness of an WSD approach in modeling word context for better word translation. This also indicates the effectiveness of our proposed cross-lingual encoders in explicitly modeling word translations to avoid wrong translations in NMT. Finally, we discuss in depth how word translations benefit different NMT frameworks from several perspectives.\n          <\/jats:p>","DOI":"10.1145\/3342353","type":"journal-article","created":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T12:17:41Z","timestamp":1563884261000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Explicitly Modeling Word Translations in Neural Machine Translation"],"prefix":"10.1145","volume":"19","author":[{"given":"Dong","family":"Han","sequence":"first","affiliation":[{"name":"School of Computer Science 8 Technology, Soochow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science 8 Technology, Soochow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yachao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science 8 Technology, Soochow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science 8 Technology, Soochow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science 8 Technology, Soochow University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,7,23]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2021"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1162"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the ICLR","author":"Bahdanau Dzmitry","year":"2015"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4716"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1177"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1304"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the NAACL","author":"Dyer Chris","year":"2013"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the ACL 2010 System Demonstrations. 7--12","author":"Dyer Chris","year":"2010"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1078"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2012"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3014"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of ICLR.","author":"Diederik"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the EMNLP","author":"Koehn Philipp","year":"2004"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1164"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1064"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1121"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the COLING","author":"Liu Lemao","year":"2016"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the AAAI","author":"Liu Yang","year":"2015"},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the EMNLP","author":"Luong Minh-Thang","year":"2015"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168054"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1249"},{"key":"e_1_2_1_23_1","unstructured":"Toan Q. Nguyen and David Chiang. 2017. Improving lexical choice in neural machine translation. Retrieved from: arXiv:1710.01329.  Toan Q. Nguyen and David Chiang. 2017. Improving lexical choice in neural machine translation. Retrieved from: arXiv:1710.01329."},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the COLING 2016. 1828","author":"Niehues Jan","year":"2016"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1120"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the WMT","author":"Rios Annette","year":"2017"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2209"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of the AMTA.","author":"Snover Matthew","year":"2006"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988237"},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of the AAAI","author":"Tu Zhaopeng","year":"2017"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the NIPS","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the AAAI","author":"Wang Xing","year":"2017"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1149"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1013"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1065"},{"key":"e_1_2_1_40_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey Jeff Klingner Apurva Shah Melvin Johnson Xiaobing Liu Lukasz Kaiser Stephan Gouws Yoshikiyo Kato Taku Kudo Hideto Kazawa Keith Stevens George Kurian Nishant Patil Wei Wang Cliff Young Jason Smith Jason Riesa Alex Rudnick Oriol Vinyals Greg Corrado Macduff Hughes and Jeffrey Dean. 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. Retrieved from: arXiv:1609.08144.  Yonghui Wu Mike Schuster Zhifeng Chen Quoc V. Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey Jeff Klingner Apurva Shah Melvin Johnson Xiaobing Liu Lukasz Kaiser Stephan Gouws Yoshikiyo Kato Taku Kudo Hideto Kazawa Keith Stevens George Kurian Nishant Patil Wei Wang Cliff Young Jason Smith Jason Riesa Alex Rudnick Oriol Vinyals Greg Corrado Macduff Hughes and Jeffrey Dean. 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. Retrieved from: arXiv:1609.08144."},{"key":"e_1_2_1_41_1","volume-title":"ADADELTA: An adaptive learning rate method. Retrieved from: arXiv:1212.5701.","author":"Zeiler Matthew D.","year":"2012"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2060"},{"key":"e_1_2_1_43_1","first-page":"30","article-title":"Multi-source neural translation","volume":"2016","author":"Zoph Barret","year":"2016","journal-title":"Proceedings of the HLT-NAACL"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342353","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3342353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:26:02Z","timestamp":1750206362000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342353"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,23]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1,31]]}},"alternative-id":["10.1145\/3342353"],"URL":"https:\/\/doi.org\/10.1145\/3342353","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,23]]},"assertion":[{"value":"2018-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-07-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}