Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Michael Zeng

Dict-BERT: Enhancing Language Model Pre-training with Dictionary


Oct 13, 2021
Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang

* Under Review 

  Access Paper or Ask Questions

Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification


Oct 12, 2021
Zhengyang Chen, Sanyuan Chen, Yu Wu, Yao Qian, Chengyi Wang, Shujie Liu, Yanmin Qian, Michael Zeng

* submitted to ICASSP 2022 

  Access Paper or Ask Questions

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering


Oct 08, 2021
Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng


  Access Paper or Ask Questions

DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization


Sep 06, 2021
Ming Zhong, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng

* Preprint 

  Access Paper or Ask Questions

Does Knowledge Help General NLU? An Empirical Study


Sep 01, 2021
Ruochen Xu, Yuwei Fang, Chenguang Zhu, Michael Zeng

* Work in Progress 

  Access Paper or Ask Questions

Want To Reduce Labeling Cost? GPT-3 Can Help


Aug 30, 2021
Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu, Michael Zeng

* Findings of EMNLP 2021, 11 pages 

  Access Paper or Ask Questions

A Joint and Domain-Adaptive Approach to Spoken Language Understanding


Jul 25, 2021
Linhao Zhang, Yu Shi, Linjun Shou, Ming Gong, Houfeng Wang, Michael Zeng


  Access Paper or Ask Questions

Retrieval Enhanced Model for Commonsense Generation


May 24, 2021
Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

* Findings of ACL-IJCNLP 2021 

  Access Paper or Ask Questions

MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization


Mar 12, 2021
Chenguang Zhu, Yang Liu, Jie Mei, Michael Zeng

* North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2021 
* Dataset: https://github.com/zcgzcgzcg1/MediaSum/ 

  Access Paper or Ask Questions

Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model


Feb 22, 2021
Junwei Liao, Yu Shi, Ming Gong, Linjun Shou, Sefik Eskimez, Liyang Lu, Hong Qu, Michael Zeng

* Accepted in 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021) 

  Access Paper or Ask Questions

Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders


Feb 12, 2021
Junwei Liao, Yu Shi, Ming Gong, Linjun Shou, Hong Qu, Michael Zeng


  Access Paper or Ask Questions

Speech-language Pre-training for End-to-end Spoken Language Understanding


Feb 11, 2021
Yao Qian, Ximo Bian, Yu Shi, Naoyuki Kanda, Leo Shen, Zhen Xiao, Michael Zeng


  Access Paper or Ask Questions

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data


Jan 19, 2021
Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang


  Access Paper or Ask Questions

Fusing Context Into Knowledge Graph for Commonsense Reasoning


Dec 09, 2020
Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, Xuedong Huang


  Access Paper or Ask Questions

LSTM-LM with Long-Term History for First-Pass Decoding in Conversational Speech Recognition


Oct 21, 2020
Xie Chen, Sarangarajan Parthasarathy, William Gale, Shuangyu Chang, Michael Zeng

* 5 pages 

  Access Paper or Ask Questions

Mixed-Lingual Pre-training for Cross-lingual Summarization


Oct 18, 2020
Ruochen Xu, Chenguang Zhu, Yu Shi, Michael Zeng, Xuedong Huang

* Accepted at Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) 2020 

  Access Paper or Ask Questions

Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding


Oct 05, 2020
Yu-An Chung, Chenguang Zhu, Michael Zeng


  Access Paper or Ask Questions

JAKET: Joint Pre-training of Knowledge Graph and Language Understanding


Oct 02, 2020
Donghan Yu, Chenguang Zhu, Yiming Yang, Michael Zeng


  Access Paper or Ask Questions

Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization


Jun 27, 2020
Beliz Gunel, Chenguang Zhu, Michael Zeng, Xuedong Huang

* NeurIPS 2019, Knowledge Representation & Reasoning Meets Machine Learning (KR2ML workshop) 

  Access Paper or Ask Questions

Meta Dialogue Policy Learning


Jun 03, 2020
Yumo Xu, Chenguang Zhu, Baolin Peng, Michael Zeng

* 10 pages, 3 figures 

  Access Paper or Ask Questions

Data Augmentation for Spoken Language Understanding via Pretrained Models


Apr 29, 2020
Baolin Peng, Chenguang Zhu, Michael Zeng, Jianfeng Gao

* 6 pages, 1 figure 

  Access Paper or Ask Questions

End-to-End Abstractive Summarization for Meetings


Apr 22, 2020
Chenguang Zhu, Ruochen Xu, Michael Zeng, Xuedong Huang

* 12 pages, 2 figures 

  Access Paper or Ask Questions

Improving Readability for Automatic Speech Recognition Transcription


Apr 09, 2020
Junwei Liao, Sefik Emre Eskimez, Liyang Lu, Yu Shi, Ming Gong, Linjun Shou, Hong Qu, Michael Zeng


  Access Paper or Ask Questions

Boosting Factual Correctness of Abstractive Summarization


Apr 04, 2020
Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang

* 17 pages, 3 figures 

  Access Paper or Ask Questions

Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph


Mar 26, 2020
Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang

* 14 pages, 2 figures 

  Access Paper or Ask Questions

Few-shot Natural Language Generation for Task-Oriented Dialog


Feb 27, 2020
Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Michael Zeng, Jianfeng Gao

* Project website: https://aka.ms/scgpt ; Code and data: https://github.com/pengbaolin/SC-GPT 

  Access Paper or Ask Questions

Make Lead Bias in Your Favor: A Simple and Effective Method for News Summarization


Jan 07, 2020
Chenguang Zhu, Ziyi Yang, Robert Gmyr, Michael Zeng, Xuedong Huang

* 7 pages, 2 figures 

  Access Paper or Ask Questions