{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:41:59Z","timestamp":1742913719196,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031414558"},{"type":"electronic","value":"9783031414565"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-41456-5_14","type":"book-chapter","created":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T23:02:43Z","timestamp":1694559763000},"page":"179-190","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the\u00a0Role of\u00a0Monolingual Data in\u00a0Cross-Attention Pre-training for\u00a0Neural Machine Translation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4419-0355","authenticated-orcid":false,"given":"Khang","family":"Pham","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0884-1635","authenticated-orcid":false,"given":"Long","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2069-1016","authenticated-orcid":false,"given":"Dien","family":"Dinh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","unstructured":"Artetxe, M., Labaka, G., Agirre, E.: A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 789\u2013798. Association for Computational Linguistics, Melbourne, Australia (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1073, https:\/\/aclanthology.org\/P18-1073","DOI":"10.18653\/v1\/P18-1073"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Artetxe, M., Labaka, G., Agirre, E., Cho, K.: Unsupervised neural machine translation. In: Sixth International Conference on Learning Representations (ICLR 2018) (2018)","DOI":"10.18653\/v1\/D18-1399"},{"key":"14_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7-9 May 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"14_CR4","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"14_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR6","unstructured":"Cettolo, M., Girardi, C., Federico, M.: Wit3: web inventory of transcribed and translated talks. In: Proceedings of the Conference of European Association for Machine Translation (EAMT), pp. 261\u2013268 (2012)"},{"key":"14_CR7","doi-asserted-by":"publisher","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747, https:\/\/aclanthology.org\/2020.acl-main.747","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"14_CR8","volume-title":"Cross-Lingual Language Model Pretraining","author":"A Conneau","year":"2019","unstructured":"Conneau, A., Lample, G.: Cross-Lingual Language Model Pretraining. Curran Associates Inc., Red Hook, NY, USA (2019)"},{"key":"14_CR9","doi-asserted-by":"publisher","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., Salakhutdinov, R.: Transformer-XL: Attentive language models beyond a fixed-length context. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2978\u20132988. Association for Computational Linguistics, Florence, Italy (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1285, https:\/\/aclanthology.org\/P19-1285","DOI":"10.18653\/v1\/P19-1285"},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"issue":"10","key":"14_CR11","first-page":"1749","volume":"19","author":"P Khang","year":"2022","unstructured":"Khang, P., Long, N.: Towards cross-attention pre-training in neural machine translation. Ho Chi Minh City Univ. Educ. J. Sci. 19(10), 1749 (2022)","journal-title":"Ho Chi Minh City Univ. Educ. J. Sci."},{"key":"14_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7-9 May 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"14_CR13","doi-asserted-by":"publisher","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703, https:\/\/aclanthology.org\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"119931","DOI":"10.1109\/ACCESS.2020.3006129","volume":"8","author":"H Li","year":"2020","unstructured":"Li, H., Sha, J., Shi, C.: Revisiting back-translation for low-resource machine translation between Chinese and Vietnamese. IEEE Access 8, 119931\u2013119939 (2020)","journal-title":"IEEE Access"},{"key":"14_CR15","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"14_CR16","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019).http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"14_CR17","doi-asserted-by":"publisher","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412\u20131421. Association for Computational Linguistics, Lisbon, Portugal (2015). https:\/\/doi.org\/10.18653\/v1\/D15-1166, https:\/\/aclanthology.org\/D15-1166","DOI":"10.18653\/v1\/D15-1166"},{"key":"14_CR18","doi-asserted-by":"publisher","unstructured":"Ott, M., et al.: fairseq: a fast, extensible toolkit for sequence modeling. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pp. 48\u201353. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-4009, https:\/\/aclanthology.org\/N19-4009","DOI":"10.18653\/v1\/N19-4009"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"14_CR20","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training. OpenAI (2018)"},{"issue":"8","key":"14_CR21","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Ren, S., Zhou, L., Liu, S., Wei, F., Zhou, M., Ma, S.: Semface: pre-training encoder and decoder with a semantic interface for neural machine translation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 4518\u20134527 (2021)","DOI":"10.18653\/v1\/2021.acl-long.348"},{"key":"14_CR23","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 86\u201396. Association for Computational Linguistics, Berlin, Germany (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1009, https:\/\/aclanthology.org\/P16-1009","DOI":"10.18653\/v1\/P16-1009"},{"key":"14_CR24","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mass: masked sequence to sequence pre-training for language generation. In: International Conference on Machine Learning (2019)"},{"key":"14_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR26","unstructured":"Zan, C., Ding, L., Shen, L., Cao, Y., Liu, W., Tao, D.: Bridging cross-lingual gaps during leveraging the multilingual sequence-to-sequence pretraining for text generation. arXiv preprint arXiv:2204.07834 (2022)"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41456-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T23:05:32Z","timestamp":1694559932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41456-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031414558","9783031414565"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41456-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"218","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"59","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.01","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.86","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}