{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T15:10:36Z","timestamp":1770995436467,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723490","type":"print"},{"value":"9783031723506","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72350-6_15","type":"book-chapter","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T12:14:50Z","timestamp":1726661690000},"page":"224-234","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improve Shallow Decoder Based Transformer with\u00a0Structured Expert Prediction"],"prefix":"10.1007","author":[{"given":"Zongbing","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingru","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Chi, Z., Dong, L., Wei, F., Wang, W., Mao, X.L., Huang, H.: Cross-lingual natural language generation via pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 7570\u20137577 (2020)","DOI":"10.1609\/aaai.v34i05.6256"},{"key":"15_CR2","doi-asserted-by":"publisher","unstructured":"Chi, Z., et al.: InfoXLM: an information-theoretic framework for cross-lingual language model pre-training. In: et al. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3576\u20133588. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.280, https:\/\/aclanthology.org\/2021.naacl-main.280","DOI":"10.18653\/v1\/2021.naacl-main.280"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: XNLI: evaluating cross-lingual sentence representations. In: EMNLP, pp. 2475\u20132485. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1269"},{"key":"15_CR4","doi-asserted-by":"publisher","unstructured":"Dou, Z., Tu, Z., Wang, X., Shi, S., Zhang, T.: Exploiting deep representations for neural machine translation. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October\u20134 November 2018, pp. 4253\u20134262. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/d18-1457","DOI":"10.18653\/v1\/d18-1457"},{"key":"15_CR5","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(120), 1\u201339 (2022). http:\/\/jmlr.org\/papers\/v23\/21-0998.html"},{"key":"15_CR6","unstructured":"Gu, J., Bradbury, J., Xiong, C., Li, V.O.K., Socher, R.: Non-autoregressive neural machine translation. In: 6th International Conference on Learning Representations. ICLR 2018, Vancouver, BC, Canada, 30 April-3 May 2018, Conference Track Proceedings. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=B1l8BtlCb"},{"key":"15_CR7","unstructured":"Hendrycks, D., Gimpel, K.: Bridging nonlinearities and stochastic regularizers with gaussian error linear units. CoRR abs\/1606.08415 (2016)"},{"issue":"1","key":"15_CR8","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"issue":"2","key":"15_CR9","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","volume":"6","author":"MI Jordan","year":"1994","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the em algorithm. Neural Comput. 6(2), 181\u2013214 (1994)","journal-title":"Neural Comput."},{"key":"15_CR10","unstructured":"Kasai, J., Pappas, N., Peng, H., Cross, J., Smith, N.: Deep encoder, shallow decoder: reevaluating non-autoregressive machine translation. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=KpfasTaLUpq"},{"key":"15_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (Poster) (2015)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Koehn, P., et\u00a0al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pp. 177\u2013180 (2007)","DOI":"10.3115\/1557769.1557821"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J.: Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: EMNLP (Demonstration), pp. 66\u201371. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-2012"},{"key":"15_CR14","unstructured":"Lample, G., Conneau, A., Ranzato, M., Denoyer, L., J\u00e9gou, H.: Word translation without parallel data (2018)"},{"key":"15_CR15","doi-asserted-by":"publisher","unstructured":"Lee, J., Mansimov, E., Cho, K.: Deterministic non-autoregressive neural sequence modeling by iterative refinement. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October\u20134 November 2018, pp. 1173\u20131182. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/d18-1149","DOI":"10.18653\/v1\/d18-1149"},{"key":"15_CR16","unstructured":"Lepikhin, D., et al.: GShard: scaling giant models with conditional computation and automatic sharding. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=qrwe7XHTmYb"},{"key":"15_CR17","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":"15_CR18","unstructured":"Ramachandran, P., Le, Q.V.: Diversity and depth in per-example routing models. In: 7th International Conference on Learning Representations. ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=BkxWJnC9tX"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. ACL 2016, 7\u201312 August 2016, Berlin, Germany, Volume 1: Long Papers. The Association for Computer Linguistics (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"15_CR20","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"15_CR21","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. In: 5th International Conference on Learning Representations. ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings. OpenReview.net (2017). https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"15_CR22","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mass: masked sequence to sequence pre-training for language generation. arXiv preprint arXiv:1905.02450 (2019)"},{"key":"15_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4\u20139 December 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1112\u20131122. Association for Computational Linguistics (2018). http:\/\/aclweb.org\/anthology\/N18-1101","DOI":"10.18653\/v1\/N18-1101"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Xing, C., Wang, D., Liu, C., Lin, Y.: Normalized word embedding and orthogonal transform for bilingual word translation. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1006\u20131011 (2015)","DOI":"10.3115\/v1\/N15-1104"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72350-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T12:17:28Z","timestamp":1726661848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72350-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723490","9783031723506"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72350-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}