{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:09:09Z","timestamp":1740100149388,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/icc42927.2021.9500450","type":"proceedings-article","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T20:49:21Z","timestamp":1628282961000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Transformer with Horizontal and Vertical Guiding Mechanisms for Neural Language Modeling"],"prefix":"10.1109","author":[{"given":"Anlin","family":"Qu","sequence":"first","affiliation":[]},{"given":"Jianwei","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Shasha","family":"Mo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2959655"},{"key":"ref32","first-page":"2766","article-title":"Dynamic evaluation of neural sequence models","author":"krause","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"Single headed attention rnn: Stop thinking with your head","year":"2019","author":"merity","key":"ref31"},{"key":"ref30","first-page":"4189","article-title":"Recurrent highway networks","author":"zilly","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"article-title":"Bp-transformer: Modelling long-range context via binary partitioning","year":"2019","author":"ye","key":"ref34"},{"key":"ref10","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref11","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013159"},{"article-title":"Language models are unsupervised multitask learners","year":"0","author":"radford","key":"ref13"},{"key":"ref14","article-title":"Low-rank bottleneck in multi-head attention models","author":"bhojanapalli","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1133"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"article-title":"Accessing higher-level representations in sequential transformers with feedback memory","year":"2020","author":"fan","key":"ref18"},{"key":"ref19","article-title":"R-transformer: Recurrent neural network enhanced transformer","author":"wang","year":"2020","journal-title":"International Conference on Learning Representations"},{"article-title":"Trellis networks for sequence modeling","year":"0","author":"bai","key":"ref28"},{"key":"ref4","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Volume 1 Long Papers)"},{"key":"ref27","first-page":"1302","article-title":"Efficient softmax approximation for gpus","author":"grave","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1152"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref29","article-title":"Hierarchical multiscale recurrent neural networks","author":"chung","year":"2019","journal-title":"5th International Conference on Learning Representations ICLR 2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Improving neural language models with a continuous cache","year":"2016","author":"grave","key":"ref8"},{"key":"ref7","article-title":"Regularizing and optimizing LSTM language models","author":"merity","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Breaking the softmax bottleneck: A high-rank RNN language model","year":"0","author":"yang","key":"ref9"},{"article-title":"Qanet: Combining local convolution with global self-attention for reading comprehension","year":"2018","author":"yu","key":"ref1"},{"article-title":"Augmenting self-attention with persistent memory","year":"2019","author":"sukhbaatar","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Reformer: The efficient transformer","year":"0","author":"kitaev","key":"ref21"},{"key":"ref24","article-title":"Pointer sentinel mixture models","author":"merity","year":"2017","journal-title":"International Conference on Learning Representations"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref23"},{"key":"ref26","article-title":"Adaptive input representations for neural language modeling","author":"baevski","year":"2019","journal-title":"International Conference on Learning Representations"},{"article-title":"Large text compression benchmark","year":"2011","author":"mahoney","key":"ref25"}],"event":{"name":"ICC 2021 - IEEE International Conference on Communications","start":{"date-parts":[[2021,6,14]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,6,23]]}},"container-title":["ICC 2021 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9500243\/9500244\/09500450.pdf?arnumber=9500450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:48:40Z","timestamp":1652197720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9500450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icc42927.2021.9500450","relation":{},"subject":[],"published":{"date-parts":[[2021,6]]}}}