{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T05:03:31Z","timestamp":1751691811641,"version":"3.41.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T00:00:00Z","timestamp":1678406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Zhengzhou University of Light Industry Doctoral Research","award":["2018BSJJ044"],"award-info":[{"award-number":["2018BSJJ044"]}]},{"name":"Xinjiang Autonomous Region University Research Plan","award":["XJEDU2017M027"],"award-info":[{"award-number":["XJEDU2017M027"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61906158"],"award-info":[{"award-number":["61906158"]}],"id":[{"id":"10.13039\/501100001809","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":[[2023,3,31]]},"abstract":"<jats:p>Parallel sentence pairs play a very important role in many natural language processing tasks, especially cross-lingual tasks such as machine translation. So far, many Asian language pairs lack bilingual parallel sentences. As collecting bilingual parallel data is very time-consuming and difficult, it is very important for many low-resource Asian language pairs. While existing methods have shown encouraging results, they rely on bilingual data seriously or have some drawbacks in an unsupervised situation. To address these issues, we propose a new unsupervised similarity calculation and dynamic selection metric to obtain parallel sentence pairs in an unsupervised situation. First, our method maps bilingual word embedding by postdoc adversarial training, which rotates the source space to match the target without parallel data. Then, we introduce a new cross-domain similarity adaption to obtain parallel sentence pairs. Experimental results on real-world datasets show that our model can obtain better accuracy and recall on mining parallel sentence pairs. We also show that the extracted bilingual sentence corpora can significantly improve the performance of neural machine translation.<\/jats:p>","DOI":"10.1145\/3486677","type":"journal-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T17:54:50Z","timestamp":1643910890000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Unsupervised Parallel Sentences of Machine Translation for Asian Language Pairs"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6412-7508","authenticated-orcid":false,"given":"Shaolin","family":"Zhu","sequence":"first","affiliation":[{"name":"Zhengzhou University of Light Industry, Zhengzhou, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenggang","family":"Mi","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, School of Computer Science ForeignLanguage and Literature Institute, Xi\u2019an International Studies University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqi","family":"Li","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Light Industry, Zhengzhou, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Yang","sequence":"additional","affiliation":[{"name":"Xinjiang Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Xu","sequence":"additional","affiliation":[{"name":"Xinjiang University of Finance and Economics, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,10]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"1853","volume-title":"Advances in Neural Information Processing Systems","author":"Chandar Sarath","year":"2014","unstructured":"Sarath Chandar, Stanislas Lauly, Hugo Larochelle, Mitesh Khapra, Balaraman Ravindran, Vikas C. Raykar, and Amrita Saha. 2014. An autoencoder approach to learning bilingual word representations. In Advances in Neural Information Processing Systems. MIT Press, 1853\u20131861."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1019"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1309"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00288"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Antonio Valerio Miceli-Barone. 2016. Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders. Retrieved from https:\/\/arXiv:1608.02996.","DOI":"10.18653\/v1\/W16-1614"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_8_2","volume-title":"Proceedings of the Workshop on Building and Using Comparable Corpora","author":"Bouamor Houda","year":"2018","unstructured":"Houda Bouamor and Hassan Sajjad. 2018. H2@bucc18: Parallel sentence extraction from comparable corpora using multilingual sentence embeddings. In Proceedings of the Workshop on Building and Using Comparable Corpora."},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Vishrav Chaudhary Yuqing Tang Francisco Guzm\u00e1n Holger Schwenk and Philipp Koehn. 2019. Low-resource corpus filtering using multilingual sentence embeddings. https:\/\/arXiv:1906.08885.","DOI":"10.18653\/v1\/W19-5435"},{"key":"e_1_3_2_10_2","first-page":"7059","volume-title":"Advances in Neural Information Processing Systems","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau and Guillaume Lample. 2019. Cross-lingual language model pretraining. In Advances in Neural Information Processing Systems. MIT Press, 7059\u20137069."},{"key":"e_1_3_2_11_2","unstructured":"Georgiana Dinu Angeliki Lazaridou and Marco Baroni. 2014. Improving zero-shot learning by mitigating the hubness problem. Retrieved from https:\/\/arXiv:1412.6568."},{"key":"e_1_3_2_12_2","first-page":"685","volume-title":"Proceedings of the 1st Conference on Machine Translation","author":"Espl\u00e0-Gomis Miquel","year":"2016","unstructured":"Miquel Espl\u00e0-Gomis, Mikel L. Forcada, Sergio Ortiz Rojas, and Jorge Ferr\u00e1ndez-Tordera. 2016. Bitextor\u2019s participation in WMT\u201916: Shared task on document alignment. In Proceedings of the 1st Conference on Machine Translation. 685\u2013691."},{"key":"e_1_3_2_13_2","first-page":"1442","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Gr\u00e9goire Francis","year":"2018","unstructured":"Francis Gr\u00e9goire and Philippe Langlais. 2018. Extracting parallel sentences with bidirectional recurrent neural networks to improve machine translation. In Proceedings of the 27th International Conference on Computational Linguistics. 1442\u20131453."},{"key":"e_1_3_2_14_2","first-page":"11","volume-title":"Proceedings of the ACL Student Research Workshop","author":"Grover Jeenu","year":"2017","unstructured":"Jeenu Grover and Pabitra Mitra. 2017. Bilingual word embeddings with bucketed cnn for parallel sentence extraction. In Proceedings of the ACL Student Research Workshop. 11\u201316."},{"key":"e_1_3_2_15_2","first-page":"165","volume-title":"Proceedings of the 3rd Conference on Machine Translation","author":"Guo Mandy","year":"2018","unstructured":"Mandy Guo, Qinlan Shen, Yinfei Yang, Heming Ge, Daniel Cer, Gustavo Hernandez Abrego, Keith Stevens, Noah Constant, Yun-Hsuan Sung, Brian Strope, et\u00a0al. 2018. Effective parallel corpus mining using bilingual sentence embeddings. In Proceedings of the 3rd Conference on Machine Translation. 165\u2013176."},{"key":"e_1_3_2_16_2","first-page":"882","volume-title":"Proceedings of the Third Conference on Machine Translation","author":"Hangya Viktor","year":"2018","unstructured":"Viktor Hangya and Alexander Fraser. 2018. An unsupervised system for parallel corpus filtering. In Proceedings of the Third Conference on Machine Translation. 882\u2013887."},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.18653\/v1\/P19-1118","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Hangya Viktor","year":"2019","unstructured":"Viktor Hangya and Alexander Fraser. 2019. Unsupervised parallel sentence extraction with parallel segment detection helps machine translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 1224\u20131234."},{"key":"e_1_3_2_18_2","unstructured":"Hany Hassan Anthony Aue Chang Chen Vishal Chowdhary Jonathan Clark Christian Federmann Xuedong Huang Marcin Junczys-Dowmunt William Lewis Mu Li et\u00a0al. 2018. Achieving human parity on automatic chinese to english news translation. Retrieved from https:\/\/arXiv:1803.05567."},{"key":"e_1_3_2_19_2","first-page":"873","volume-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics","author":"Huang Eric H.","year":"2012","unstructured":"Eric H. Huang, Richard Socher, Christopher D. Manning, and Andrew Y. Ng. 2012. Improving word representations via global context and multiple word prototypes. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. 873\u2013882."},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Marcin Junczys-Dowmunt. 2018. Dual conditional cross-entropy filtering of noisy parallel corpora. Retrieved from https:\/\/arXiv:1809.00197.","DOI":"10.18653\/v1\/W18-6478"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.18653\/v1\/D19-1138","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP\u201919)","author":"Keung Phillip","year":"2019","unstructured":"Phillip Keung, Vikas Bhardwaj, et\u00a0al. 2019. Adversarial learning with contextual embeddings for zero-resource cross-lingual classification and NER. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP\u201919). 1355\u20131360."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00348"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"74","DOI":"10.18653\/v1\/W18-2709","volume-title":"Proceedings of the 2nd Workshop on Neural Machine Translation and Generation","author":"Khayrallah Huda","year":"2018","unstructured":"Huda Khayrallah and Philipp Koehn. 2018. On the impact of various types of noise on neural machine translation. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation. 74\u201383."},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Yunsu Kim Hendrik Rosendahl Nick Rossenbach Jan Rosendahl Shahram Khadivi and Hermann Ney. 2019. Learning bilingual sentence embeddings via autoencoding and computing similarities with a multilayer perceptron. Retrieved from https:\/\/arXiv:1906.01942.","DOI":"10.18653\/v1\/W19-4309"},{"key":"e_1_3_2_25_2","first-page":"726","volume-title":"Proceedings of the 3rd Conference on Machine Translation","author":"Koehn Philipp","year":"2018","unstructured":"Philipp Koehn, Huda Khayrallah, Kenneth Heafield, and Mikel L. Forcada. 2018. Findings of the WMT 2018 shared task on parallel corpus filtering. In Proceedings of the 3rd Conference on Machine Translation. 726\u2013739."},{"key":"e_1_3_2_26_2","first-page":"255","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Kvapil\u00edkov\u00e1 Ivana","year":"2020","unstructured":"Ivana Kvapil\u00edkov\u00e1, Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Ond\u0159ej Bojar. 2020. Unsupervised multilingual sentence embeddings for parallel corpus mining. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 255\u2013262."},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Lample Guillaume","year":"2018","unstructured":"Guillaume Lample, Alexis Conneau, Marc\u2019Aurelio Ranzato, Ludovic Denoyer, and Herv\u00e9 J\u00e9gou. 2018. Word translation without parallel data. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_28_2","first-page":"392","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","author":"Marie Benjamin","year":"2017","unstructured":"Benjamin Marie and Atsushi Fujita. 2017. Efficient extraction of pseudo-parallel sentences from raw monolingual data using word embeddings. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 392\u2013398."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220186"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392048"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","first-page":"4990","DOI":"10.18653\/v1\/P19-1492","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Ormazabal Aitor","year":"2019","unstructured":"Aitor Ormazabal, Mikel Artetxe, Gorka Labaka, Aitor Soroa, and Eneko Agirre. 2019. Analyzing the limitations of cross-lingual word embedding mappings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 4990\u20134995."},{"key":"e_1_3_2_32_2","first-page":"3476","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Ren Shuo","year":"2020","unstructured":"Shuo Ren, Shujie Liu, Ming Zhou, and Shuai Ma. 2020. A graph-based coarse-to-fine method for unsupervised bilingual lexicon induction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 3476\u20133485."},{"key":"e_1_3_2_33_2","unstructured":"Ali Sabet Prakhar Gupta Jean-Baptiste Cordonnier Robert West and Martin Jaggi. 2019. Robust cross-lingual embeddings from parallel sentences. Retrieved from https:\/\/arXiv:1912.12481."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Holger Schwenk. 2018. Filtering and mining parallel data in a joint multilingual space. Retrieved from https:\/\/arXiv:1805.09822.","DOI":"10.18653\/v1\/P18-2037"},{"key":"e_1_3_2_35_2","unstructured":"Holger Schwenk Guillaume Wenzek Sergey Edunov Edouard Grave and Armand Joulin. 2019. Ccmatrix: Mining billions of high-quality parallel sentences on the web. Retrieved from https:\/\/arXiv:1911.04944."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJAIP.2013.056421"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.5120\/8526-2129"},{"key":"e_1_3_2_38_2","first-page":"403","volume-title":"Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technologies","author":"Smith Jason","year":"2010","unstructured":"Jason Smith, Chris Quirk, and Kristina Toutanova. 2010. Extracting parallel sentences from comparable corpora using document level alignment. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technologies. 403\u2013411."},{"key":"e_1_3_2_39_2","first-page":"403","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL\u201910)","author":"Smith Jason R.","year":"2010","unstructured":"Jason R. Smith, Chris Quirk, and Kristina Toutanova. 2010. Extracting parallel sentences from comparable corpora using document level alignment. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL\u201910). Association for Computational Linguistics, 403\u2013411."},{"issue":"3","key":"e_1_3_2_40_2","first-page":"32:1\u201332:22","article-title":"Leveraging additional resources for improving statistical machine translation on Asian low-resource languages","volume":"18","author":"Trieu Hai-Long","year":"2019","unstructured":"Hai-Long Trieu, Duc-Vu Tran, Ashwin Ittoo, and Le-Minh Nguyen. 2019. Leveraging additional resources for improving statistical machine translation on Asian low-resource languages. ACM Trans. Asian Low Resour. Lang. Info. Process. 18, 3 (2019), 32:1\u201332:22.","journal-title":"ACM Trans. Asian Low Resour. Lang. Info. Process."},{"key":"e_1_3_2_41_2","first-page":"1959","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","author":"Zhang Meng","year":"2017","unstructured":"Meng Zhang, Yang Liu, Huanbo Luan, and Maosong Sun. 2017. Adversarial training for unsupervised bilingual lexicon induction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 1959\u20131970."},{"key":"e_1_3_2_42_2","first-page":"2870","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201916)","author":"Zhang Meng","year":"2016","unstructured":"Meng Zhang, Yang Liu, Huan-Bo Luan, Maosong Sun, Tatsuya Izuha, and Jie Hao. 2016. Building earth mover\u2019s distance on bilingual word embeddings for machine translation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201916). 2870\u20132876."},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","first-page":"51","DOI":"10.18653\/v1\/W17-2510","volume-title":"Proceedings of the 10th Workshop on Building and Using Comparable Corpora","author":"Zhang Zheng","year":"2017","unstructured":"Zheng Zhang and Pierre Zweigenbaum. 2017. zNLP: Identifying parallel sentences in Chinese-English comparable corpora. In Proceedings of the 10th Workshop on Building and Using Comparable Corpora. 51\u201355."},{"key":"e_1_3_2_44_2","first-page":"8823906:1\u201388239","article-title":"Extracting parallel sentences from nonparallel corpora using parallel hierarchical attention network","volume":"2020","author":"Zhu Shaolin","year":"2020","unstructured":"Shaolin Zhu, Yong Yang, and Chun Xu. 2020. Extracting parallel sentences from nonparallel corpora using parallel hierarchical attention network. Comput. Intell. Neurosci. 2020 (2020), 8823906:1\u20138823906:9.","journal-title":"Comput. Intell. Neurosci."}],"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\/3486677","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3486677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:46Z","timestamp":1750191526000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3486677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,10]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3,31]]}},"alternative-id":["10.1145\/3486677"],"URL":"https:\/\/doi.org\/10.1145\/3486677","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2023,3,10]]},"assertion":[{"value":"2021-04-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}