{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:49:39Z","timestamp":1743000579066,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601219"},{"type":"electronic","value":"9789819601226"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0122-6_6","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:23:25Z","timestamp":1731781405000},"page":"54-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Parameter-Efficient Transformers with\u00a0Contrastive Syntax and\u00a0Regularized Dropout for\u00a0Neural Machine Translation"],"prefix":"10.1007","author":[{"given":"Yunlong","family":"Fan","sequence":"first","affiliation":[]},{"given":"Zhiheng","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Baixuan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"6_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008 (2017)"},{"key":"6_CR2","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., Uszkoreit, J., Kaiser, U.: Universal transformers. In: Proceedings of the 7th ICLR (2019)"},{"key":"6_CR3","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. CoRR abs\/1909.11942, 1\u201317 (2020)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Takase, S., Kiyono, S.: Lessons on parameter sharing across layers in transformers. In: Proceedings of the 4th Workshop on Simple and Efficient Natural Language Processing, pp. 78\u201390 (2023)","DOI":"10.18653\/v1\/2023.sustainlp-1.5"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Ge, T., Chen, S.Q., Wei, F.: EdgeFormer: a parameter-efficient transformer for on-device seq2seq generation. In: Proceedings of EMNLP, pp. 10786\u201310798 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.741"},{"issue":"1","key":"6_CR6","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Varis, D., Bojar, O.: Sequence length is a domain: length-based overfitting in transformer models. In: Proceedings of EMNLP, pp. 8246\u20138257 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.650"},{"key":"6_CR8","unstructured":"Junczys-Dowmunt, M., Dwojak, T., Hoang, H.: Is neural machine translation ready for deployment? A case study on 30 translation directions. In: Proceedings of the 13th International Conference on Spoken Language Translation (2016)"},{"key":"6_CR9","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. (2014)"},{"key":"6_CR10","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd ICLR (2015)"},{"key":"6_CR11","unstructured":"Hassan, H., et al.: Achieving human parity on automatic Chinese to English news translation. CoRR abs\/1803.05567 (2018)"},{"key":"6_CR12","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 NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: UniDrop: a simple yet effective technique to improve transformer without extra cost. In: Proceedings of the 2021 Conference of NAACL-HLT, pp. 3865\u20133878 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.302"},{"key":"6_CR14","first-page":"10890","volume":"34","author":"X Liang","year":"2021","unstructured":"Liang, X., et al.: R-drop: regularized dropout for neural networks. Adv. Neural. Inf. Process. Syst. 34, 10890\u201310905 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Huck, M., Hoang, H., Koehn, P.: Augmenting string-to-tree and tree-to-string translation with non-syntactic phrases. In: Proceedings of the 9th Workshop on Statistical Machine Translation, pp. 486\u2013498 (2014)","DOI":"10.3115\/v1\/W14-3362"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Deguchi, H., Tamura, A., Ninomiya, T.: Dependency-based self-attention for transformer NMT. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing, pp. 239\u2013246 (2019)","DOI":"10.26615\/978-954-452-056-4_028"},{"key":"6_CR17","unstructured":"Wang, C., Wu, S., Liu, S.: Source dependency-aware transformer with supervised self-attention. CoRR abs\/1909.02273 (2019)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Bugliarello, E., Okazaki, N.: Enhancing machine translation with dependency-aware self-attention. In: Proceedings of the 58th ACL, pp. 1618\u20131627 (2020)","DOI":"10.18653\/v1\/2020.acl-main.147"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., Manning, C.D.: Stanza: a python natural language processing toolkit for many human languages. In: Proceedings of the 58th ACL, pp. 101\u2013108 (2020)","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Apell\u00e1niz, P.A., Jim\u00e9nez, A., Galende, B.A., Parras, J., Zazo, S.: Synthetic tabular data validation: a divergence-based approach. CoRR abs\/2405.07822 (2024)","DOI":"10.1109\/ACCESS.2024.3434582"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, H., Qiu, S., Duan, X., Zhang, M.: Token drop mechanism for neural machine translation. In: Proceedings of the 28th ICCL, pp. 4298\u20134303 (2020)","DOI":"10.18653\/v1\/2020.coling-main.379"},{"key":"6_CR22","unstructured":"Shen, D., Zheng, M., Shen, Y., Qu, Y., Chen, W.: A simple but tough-to-beat data augmentation approach for natural language understanding and generation. CoRR abs\/2009.13818 (2020)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Fan, Z., et al.: Mask attention networks: Rethinking and strengthen transformer. In: Proceedings of the 2021 Conference of NAACL-HLT, pp. 1692\u20131701 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.135"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Gao, P., He, Z., Wu, H., Wang, H.: Bi-SimCut: a simple strategy for boosting neural machine translation. In: Proceedings of the 2022 Conference of NAACL-HLT, pp. 3938\u20133948 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.289"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0122-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T19:17:15Z","timestamp":1731784635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0122-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601219","9789819601226"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0122-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}