{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:25Z","timestamp":1750220845123,"version":"3.41.0"},"reference-count":26,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T00:00:00Z","timestamp":1566345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Mongolian Language Information Special Support Project of Inner Mongolia","award":["MW-2018-MGYWXXH-302"],"award-info":[{"award-number":["MW-2018-MGYWXXH-302"]}]},{"DOI":"10.13039\/501100004763","name":"Natural Science Foundation of Inner Mongolia","doi-asserted-by":"crossref","award":["2018MS06005"],"award-info":[{"award-number":["2018MS06005"]}],"id":[{"id":"10.13039\/501100004763","id-type":"DOI","asserted-by":"crossref"}]}],"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            Nearly all of the work in neural machine translation (NMT) is limited to a quite restricted vocabulary, crudely treating all other words the same as an &lt;\n            <jats:italic>unk<\/jats:italic>\n            &gt; symbol. For the translation of language with abundant morphology, unknown (UNK) words also come from the misunderstanding of the translation model to the morphological changes. In this study, we explore two ways to alleviate the UNK problem in NMT: a new generative adversarial network (added value constraints and semantic enhancement) and a preprocessing technique that mixes morphological noise. The training process is like a win-win game in which the players are three adversarial sub models (generator, filter, and discriminator). In this game, the filter is to emphasize the discriminator\u2019s attention to the negative generations that contain noise and improve the training efficiency. Finally, the discriminator cannot easily discriminate the negative samples generated by the generator with filter and human translations. The experimental results show that the proposed method significantly improves over several strong baseline models across various language pairs and the newly emerged Mongolian-Chinese task is state-of-the-art.\n          <\/jats:p>","DOI":"10.1145\/3342482","type":"journal-article","created":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T11:40:27Z","timestamp":1566387627000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Adversarial Training for Unknown Word Problems in Neural Machine Translation"],"prefix":"10.1145","volume":"19","author":[{"given":"Yatu","family":"Ji","sequence":"first","affiliation":[{"name":"Computer Science Department, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxu","family":"Hou","sequence":"additional","affiliation":[{"name":"Computer Science Department, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Computer Science Department, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nier","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Science Department, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,8,21]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv 1409 0473.  Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv 1409 0473."},{"key":"e_1_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Xilun Chen Yu Sun etal 2016. Adversarial deep averaging networks for cross-lingual sentiment classification. In Association for Computational Linguistics (ACL\u201916). 557--570.  Xilun Chen Yu Sun et al. 2016. Adversarial deep averaging networks for cross-lingual sentiment classification. In Association for Computational Linguistics (ACL\u201916). 557--570.","DOI":"10.1162\/tacl_a_00039"},{"key":"e_1_2_1_3_1","unstructured":"J. Chung C. Gulcehre K. H. Cho etal 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv 4 3555.  J. Chung C. Gulcehre K. H. Cho et al. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv 4 3555."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/089892903321107891"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510310"},{"key":"e_1_2_1_6_1","volume-title":"International Conference on Machine Learning (ICML\u201917)","author":"Gehring Jonas","year":"2017","unstructured":"Jonas Gehring , Michael Auli , David Grangier , 2017 . Convolutional sequence to sequence learning . In International Conference on Machine Learning (ICML\u201917) . 1243--1252. Jonas Gehring, Michael Auli, David Grangier, et al. 2017. Convolutional sequence to sequence learning. In International Conference on Machine Learning (ICML\u201917). 1243--1252."},{"key":"e_1_2_1_7_1","unstructured":"Alex Graves. 2013. Generating sequences with recurrent neural networks. arXiv preprint arXiv 1308.0850.  Alex Graves. 2013. Generating sequences with recurrent neural networks. arXiv preprint arXiv 1308.0850."},{"key":"e_1_2_1_8_1","unstructured":"Caglar Gulcehre Sungjin Ahn etal 2016. Pointing the unknown words. In Association for Computational Linguistics (ACL\u201916). 140--149.  Caglar Gulcehre Sungjin Ahn et al. 2016. Pointing the unknown words. In Association for Computational Linguistics (ACL\u201916). 140--149."},{"key":"e_1_2_1_9_1","volume-title":"Conference and Workshop on Neural Information Processing Systems (NIPS\u201915)","author":"Hermann Karl Moritz","year":"2015","unstructured":"Karl Moritz Hermann , Tom\u00e1\u015d Ko\u0109isk\u00fd , 2015 . Teaching machines to read and comprehend . In Conference and Workshop on Neural Information Processing Systems (NIPS\u201915) . 1693--1701. Karl Moritz Hermann, Tom\u00e1\u015d Ko\u0109isk\u00fd, et al. 2015. Teaching machines to read and comprehend. In Conference and Workshop on Neural Information Processing Systems (NIPS\u201915). 1693--1701."},{"key":"e_1_2_1_10_1","unstructured":"S\u00e9bastien Jean Kyunghyun Cho etal 2015. On using very large target vocabulary for neural machine translation. In Association for Computational Linguistics (ACL\u201915). 1--10.  S\u00e9bastien Jean Kyunghyun Cho et al. 2015. On using very large target vocabulary for neural machine translation. In Association for Computational Linguistics (ACL\u201915). 1--10."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1002"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2006.11.005"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"e_1_2_1_14_1","unstructured":"Volodymyr Mnih Koray Kavukcuoglu etal 2013. Playing Atari with deep reinforcement learning. arXiv 1312.5602 (2013).  Volodymyr Mnih Koray Kavukcuoglu et al. 2013. Playing Atari with deep reinforcement learning. arXiv 1312.5602 (2013)."},{"key":"e_1_2_1_15_1","volume-title":"International Conference on Artificial Intelligence and Statistics (AiStats\u201905)","author":"Morin Frederic","year":"2005","unstructured":"Frederic Morin and Yoshua Bengio . 2005 . Hierarchical probabilistic neural network language model . In International Conference on Artificial Intelligence and Statistics (AiStats\u201905) . 246--252. Frederic Morin and Yoshua Bengio. 2005. Hierarchical probabilistic neural network language model. In International Conference on Artificial Intelligence and Statistics (AiStats\u201905). 246--252."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_2_1_17_1","unstructured":"Marc\u2019Aurelio Ranzato Sumit Chopra etal 2015. Sequence level training with recurrent neural networks. arXiv 1511.06732 (2015).  Marc\u2019Aurelio Ranzato Sumit Chopra et al. 2015. Sequence level training with recurrent neural networks. arXiv 1511.06732 (2015)."},{"volume-title":"Neural machine translation of rare words with subword units","author":"Sennrich Rico","key":"e_1_2_1_18_1","unstructured":"Rico Sennrich , Barry Haddow , and Alexandra Birch . 2016. Neural machine translation of rare words with subword units . In Association for Computational Linguistics (ACL\u2019 16). 1715--1725. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Association for Computational Linguistics (ACL\u201916). 1715--1725."},{"volume-title":"Conference and Workshop on Neural Information Processing Systems (NIPS\u201914)","author":"Sutskever Ilya","key":"e_1_2_1_19_1","unstructured":"Ilya Sutskever , Oriol Vinyals , and Quoc V. Le . 2014. Sequence to sequence learning with neural networks . In Conference and Workshop on Neural Information Processing Systems (NIPS\u201914) . 3104--3112. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Conference and Workshop on Neural Information Processing Systems (NIPS\u201914). 3104--3112."},{"key":"e_1_2_1_20_1","unstructured":"A. Tamar Y. Wu G. Thomas etal 2016. Value iteration networks. In Neural Information Processing Systems (NIPS\u201916). 2154--2162.   A. Tamar Y. Wu G. Thomas et al. 2016. Value iteration networks. In Neural Information Processing Systems (NIPS\u201916). 2154--2162."},{"key":"e_1_2_1_21_1","volume-title":"Conference and Workshop on Neural Information Processing Systems (NIPS\u201917)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , 2017 . Attention is all you need . In Conference and Workshop on Neural Information Processing Systems (NIPS\u201917) . 5998--6008. Ashish Vaswani, Noam Shazeer, et al. 2017. Attention is all you need. In Conference and Workshop on Neural Information Processing Systems (NIPS\u201917). 5998--6008."},{"key":"e_1_2_1_22_1","volume-title":"Asian Conference on Machine Learning (ACML\u201918)","author":"Wu L.","year":"2018","unstructured":"L. Wu , Y. Xia , L. Zhao , 2018 . Adversarial neural machine translation . In Asian Conference on Machine Learning (ACML\u201918) . 374--385. L. Wu, Y. Xia, L. Zhao, et al. 2018. Adversarial neural machine translation. In Asian Conference on Machine Learning (ACML\u201918). 374--385."},{"volume-title":"SeqGAN: Sequence generative adversarial nets with policy gradient","author":"Yu Lantao","key":"e_1_2_1_23_1","unstructured":"Lantao Yu , Weinan Zhang , Jun Wang , and Yong Yu. 2016. SeqGAN: Sequence generative adversarial nets with policy gradient . In The Association for the Advancement of Artificial Intelligence (AAAI\u201916). 2852--2858. Lantao Yu, Weinan Zhang, Jun Wang, and Yong Yu. 2016. SeqGAN: Sequence generative adversarial nets with policy gradient. In The Association for the Advancement of Artificial Intelligence (AAAI\u201916). 2852--2858."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00077"},{"key":"e_1_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Zhen Yang Wei Chen Feng Wang and Bo Xu. 2018. Improving neural machine translation with conditional sequence generative adversarial nets. In The North American Chapter of the Association for Computational Linguistics (NAACL\u201918). 1346--1355.  Zhen Yang Wei Chen Feng Wang and Bo Xu. 2018. Improving neural machine translation with conditional sequence generative adversarial nets. In The North American Chapter of the Association for Computational Linguistics (NAACL\u201918). 1346--1355.","DOI":"10.18653\/v1\/N18-1122"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"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\/3342482","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3342482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:00Z","timestamp":1750202580000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,21]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1,31]]}},"alternative-id":["10.1145\/3342482"],"URL":"https:\/\/doi.org\/10.1145\/3342482","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2019,8,21]]},"assertion":[{"value":"2019-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-08-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}