PDF下载 分享
[1]张鹏远,等.基于预训练语言表示模型的汉语韵律结构预测[J].天津大学学报(自然科学与工程技术版),2020,53(03):265-271.[doi:10.11784/tdxbz201901086]
 Zhang Pengyuan,Lu Chunhui,et al.Chinese Prosodic Structure Prediction Based on a Pretrained Language Representation Model[J].Journal of Tianjin University(Science and Technology),2020,53(03):265-271.[doi:10.11784/tdxbz201901086]
点击复制

基于预训练语言表示模型的汉语韵律结构预测

参考文献/References:

[1] Wang M Q,Hirschberg J. Predicting intonational phrasing from text[C]// Proceedings of the 29th Annu-al Meeting of the Association for Computational Lin-guistics. California,USA,1991:285-292.

[2] 聂 鑫,王作英. 汉语语句中短语间停顿的自动预测方法[J]. 中文信息学报,2003,17(4):40-45.

Nie Xin,Wang Zuoying. Automatic phrase prediction in Chinese sentences[J]. Journal of Chinese Infor-mation Processing,2003,17(4):40-45(in Chi-nese).

[3] 李剑锋,胡国平,王仁华. 基于最大熵模型的韵律短语边界预测[J]. 中文信息学报,2004,18(5):57-64.

Li Jianfeng,Hu Guoping,Wang Renhua. Prosody phrase break prediction based on maximum entropy model[J]. Journal of Chinese Information Processing,2004,18(5):57-64(in Chinese).

[4] Qian Yao,Wu Zhizheng,Ma Xuezhe,et al. Automat-ic prosody prediction and detection with conditional random field models[C]// Proceedings of the 7th Inter-national Symposium on Chinese Spoken Language Pro-cessing. Tainan,China,2010:135-138.

[5] Andrew M D,Quoc V L. Semi-supervised sequence learning[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal,Canada,2015:3079-3087.

[6] Matthew P,Waleed A,Chandra B,et al. Semi-supervised sequence tagging with bidirectional language models[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Van-cou-ver,Canada,2017:1756-1765.

[7] Jeremy H,Sebastian R. Universal language model fine-tuning for text classification[C]// Proceedings of the 56th Annual Meeting of the Association for Compu-tational Linguistics. Melbourne,Australia,2018:328-339.

[8] Ding Chuang,Xie Lei,Yan Jie,et al. Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features[C]// IEEE workshop on Automatic Speech Recognition and Un-derstanding. Scottsdale,USA,2015:98-102.

[9] Zhao Yi,Ding Chuang,Nobuaki M,et al. A study on BLSTM-RNN-based Chinese prosodic structure predic-tion in a unified framework with character-level fea-tures [C]// Proceedings of Speech Prosody. Boston,USA,2016:64-68.

[10] Zheng Yibin,Li Ya,Wen Zhengqi,et al. Improving prosodic boundaries prediction for mandarin speech synthesis by using enhanced embedding feature and model fusion approach[C]// Proceedings of the 17th Annual Conference of the International Speech Com-munication Association. San Francisco,USA,2016:3201-3205.

[11] Zheng Yibin,Tao Jianhua,Wen Zhengqi,et al. BLSTM-CRF based end-to-end prosodic boundary pre-diction with context sensitive embeddings in a text-to-speech front-end[C]// Proceedings of the 19th Annual Conference of the International Speech Communica-tion Association. Hyderabad,India,2018:47-51.

[12] Huang Yuchen,Wu Zhiyong,Li Runnan,et al. Mul-ti-task learning for prosodic structure generation using BLSTM RNN with structured output layer[C]// Pro-ceedings of the 18th Annual Conference of the Interna-tional Speech Communication Association. Stockholm,Sweden,2017:779-783.

[13] Lu Chunhui,Zhang Pengyuan,Yan Yonghong. Self-attention based prosodic boundary prediction for Chi-nese speech synthesis[C]// Proceedings of the Interna-tional Conference on Acoustics,Speech and Signal Processing. Brighton,United Kingdom,2019:7035-7039.

[14] Devlin J,Chang MingWei,Lee K,et al. BERT:Pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Confer-ence of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis,USA,2019:4171-4186.

[15] Ashish V,Noam S,Niki P,et al. Attention is all you need[C]// Proceedings of the 30th International Con-ference on Neural Information Processing Systems. Long Beach,USA,2017:5998-6008.

[16] He Kaiming,Zhang Xiangyu,Ren Shaoqing,et al. Deep residual learning for image recognition[C] // IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA,2016:770-778.

[17] Jimmy L B,Jamie R K,Geoffrey E H. Layer normal-ization[EB/OL]. https://arxiv.org/abs/1607.06450,2016-07-21.

[18] Vinod N,Geoffrey E H. Rectified linear units improve restricted boltzmann machines[C]// Proceedings of the 27th International Conference on Machine Learning. Haifa,Israel,2010:807-814.

[19] Diederik K,Jimmy B. Adam:A method for stochastic optimization[EB/OL]. https://arxiv.org/abs/1412.6980,2017-01-30.

[20] Kudo T. CRF++:Yet another CRF toolkit[EB/OL]. https://taku910.github.io/crfpp/,2013-02-13.

[21] Martin A,Paul B,Chen Jianmin,et al. TensorFlow:A system for large-scale machine learning [C] // Pro-ceedings of the 12th USENIX Conference on Operating Systems Design and Implementation. Savannah,USA,2016:265-283.


备注/Memo

通信作者:张鹏远,zhangpengyuan@hccl.ioa.ac.cn.

更新日期/Last Update: 2020-03-04