{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T20:04:42Z","timestamp":1745352282322,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706667","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T22:58:35Z","timestamp":1558393115000},"page":"250-254","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Head Attention for End-to-End Neural Machine Translation"],"prefix":"10.1109","author":[{"given":"Ivan","family":"Fung","sequence":"first","affiliation":[]},{"given":"Brian","family":"Mak","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"One model to learn them all","author":"kaiser","year":"2017","journal-title":"arXiv preprint arXiv 1706 05137"},{"key":"ref11","article-title":"Constituency parsing with a selfattentive encoder","author":"kitaev","year":"2018","journal-title":"arXiv preprint arXiv 1805 01052"},{"key":"ref12","article-title":"Linguistically-informed self-attention for semantic role labeling","author":"strubell","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11928","article-title":"Deep semantic role labeling with self-attention","author":"tan","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref14","article-title":"QANet: Combining local convolution with global self-attention for reading comprehension","author":"yu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref15","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref16","article-title":"Stateof-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2018","journal-title":"International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","article-title":"Multihead decoder for end-to-end speech recognition","author":"hayashi","year":"2018","journal-title":"arXiv preprint arXiv 1804 00209"},{"key":"ref18","article-title":"Improving the performance of online neural transducer models","author":"sainath","year":"2017","journal-title":"arXiv preprint arXiv 1712 01807"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref3","first-page":"1700","article-title":"Recurrent continuous translation models","author":"kalchbrenner","year":"2013","journal-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref7","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815829"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075117"},{"key":"ref9","article-title":"Endto- end dense video captioning with masked transformer","author":"zhou","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref20","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1151"},{"key":"ref23","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2018,11,26]]},"location":"Taipei City, Taiwan","end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706667.pdf?arnumber=8706667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T19:28:55Z","timestamp":1694892535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706667","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}