{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T09:14:49Z","timestamp":1771665289236,"version":"3.50.1"},"reference-count":51,"publisher":"MIT Press - Journals","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Linguistics"],"published-print":{"date-parts":[[2019,6]]},"abstract":"<jats:p> Neural machine translation (NMT) has shown great success as a new alternative to the traditional Statistical Machine Translation model in multiple languages. Early NMT models are based on sequence-to-sequence learning that encodes a sequence of source words into a vector space and generates another sequence of target words from the vector. In those NMT models, sentences are simply treated as sequences of words without any internal structure. In this article, we focus on the role of the syntactic structure of source sentences and propose a novel end-to-end syntactic NMT model, which we call a tree-to-sequence NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our proposed model has an attention mechanism that enables the decoder to generate a translated word while softly aligning it with phrases as well as words of the source sentence. We have empirically compared the proposed model with sequence-to-sequence models in various settings on Chinese-to-Japanese and English-to-Japanese translation tasks. Our experimental results suggest that the use of syntactic structure can be beneficial when the training data set is small, but is not as effective as using a bi-directional encoder. As the size of training data set increases, the benefits of using a syntactic tree tends to diminish. <\/jats:p>","DOI":"10.1162\/coli_a_00348","type":"journal-article","created":{"date-parts":[[2019,3,20]],"date-time":"2019-03-20T18:09:55Z","timestamp":1553105395000},"page":"267-292","source":"Crossref","is-referenced-by-count":9,"title":["Incorporating Source-Side Phrase Structures into Neural Machine Translation"],"prefix":"10.1162","volume":"45","author":[{"given":"Akiko","family":"Eriguchi","sequence":"first","affiliation":[{"name":"Microsoft Research."}]},{"given":"Kazuma","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"Salesforce Research."}]},{"given":"Yoshimasa","family":"Tsuruoka","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Department of Information and Communication Engineering."}]}],"member":"281","reference":[{"key":"bib1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2021"},{"key":"bib2","volume-title":"Proceedings of International Conference on Learning Representations 2015","author":"Bahdanau Dzmitry","year":"2015"},{"key":"bib3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1209"},{"key":"bib4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4303"},{"key":"bib5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1177"},{"key":"bib6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"bib7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"bib8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1004"},{"key":"bib9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1024"},{"key":"bib10","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"bib11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1078"},{"key":"bib12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2012"},{"key":"bib13","series-title":"Proceedings of Machine Learning Research","first-page":"1243","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"Gehring Jonas","year":"2017"},{"key":"bib14","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"issue":"1","key":"bib15","first-page":"307","volume":"13","author":"Gutmann Michael U.","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"bib16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1012"},{"key":"bib17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"bib18","first-page":"944","volume-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing","author":"Isozaki Hideki","year":"2010"},{"key":"bib19","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"Ji Shihao","year":"2016"},{"key":"bib20","first-page":"2342","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"37","author":"J\u00f3zefowicz Rafal","year":"2015"},{"key":"bib21","first-page":"1700","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Kalchbrenner Nal","year":"2013"},{"key":"bib22","first-page":"388","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing","author":"Koehn Philipp","year":"2004"},{"key":"bib23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"bib24","first-page":"69","volume-title":"Proceedings of the 2nd Workshop on Asian Translation (WAT2015)","author":"Lee Hyoung Gyu","year":"2015"},{"key":"bib25","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075152"},{"key":"bib26","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220252"},{"key":"bib27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"bib28","first-page":"3111","volume-title":"Advances in Neural Information Processing Systems 26","author":"Mikolov Tomas","year":"2013"},{"key":"bib29","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.34.1.35"},{"key":"bib30","first-page":"1","volume-title":"Proceedings of the 2nd Workshop on Asian Translation (WAT2015)","author":"Nakazawa Toshiaki","year":"2015"},{"key":"bib31","first-page":"2204","volume-title":"Proceedings of the 10th Conference on International Language Resources and Evaluation","author":"Nakazawa Toshiaki","year":"2016"},{"key":"bib32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2024"},{"key":"bib33","first-page":"35","volume-title":"Proceedings of the 2nd Workshop on Asian Translation (WAT2015)","author":"Neubig Graham","year":"2015"},{"key":"bib34","first-page":"529","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Neubig Graham","year":"2011"},{"key":"bib35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1079"},{"key":"bib36","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002"},{"key":"bib37","author":"Pascanu Razvan","year":"2012","journal-title":"arXiv: 1211.5063"},{"key":"bib38","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(90)90005-K"},{"key":"bib39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4009"},{"key":"bib40","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.165"},{"key":"bib41","volume-title":"Syntactic Theory: A Formal Introduction","author":"Sag Ivan A.","year":"2003","edition":"2"},{"key":"bib42","first-page":"3104","volume-title":"Advances in Neural Information Processing Systems 27","author":"Sutskever Ilya","year":"2014"},{"key":"bib43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1150"},{"key":"bib44","first-page":"25","volume-title":"Proceedings of the 2nd Workshop on Neural Machine Translation and Generation","author":"Tran Ke","year":"2018"},{"key":"bib45","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017"},{"key":"bib46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1065"},{"key":"bib47","author":"Wu Yonghui","year":"2016","journal-title":"arXiv preprint arXiv:1609.08144"},{"key":"bib48","doi-asserted-by":"publisher","DOI":"10.3115\/1073012.1073079"},{"key":"bib49","volume-title":"Proceedings of International Conference on Learning Representations 2017","author":"Yoon Kim","year":"2017"},{"key":"bib50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00105"},{"key":"bib51","first-page":"61","volume-title":"Proceedings of the 2nd Workshop on Asian Translation (WAT2015)","author":"Zhu Zhongyuan","year":"2015"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/coli_a_00348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:28:23Z","timestamp":1615584503000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/45\/2\/267-292\/1633"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["10.1162\/coli_a_00348"],"URL":"https:\/\/doi.org\/10.1162\/coli_a_00348","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6]]}}}