Peng Li

Pattern Recognition Center, WeChat AI, Tencent Inc

Contact: pengli09 at gmail.com

Publications

• Qiu Ran*, Yankai Lin*, Peng Li*, Jie Zhou. Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation. Proceedings of ACL 2020. [pdf]
• Xu Han, Yi Dai, Tianyu Gao, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou. Continual Relation Learning via Episodic Memory Activation and Reconsolidation. Proceedings of ACL 2020. [pdf]
• Deli Chen, Yankai Lin, Wei Li, Peng Li, Jie Zhou, Xu Sun. Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View. Proceedings of AAAI 2020, New York, USA. [pdf]
• Feilong Chen, Fandong Meng, Jiaming Xu, Peng Li, Bo Xu, Jie Zhou. DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog. Proceedings of AAAI 2020, New York, USA. [pdf] [code]
• Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, and Zhiyuan Liu. NumNet: Machine Reading Comprehension with Numerical Reasoning. Proceedings of EMNLP 2019, Hong Kong, China, pp. 2474-2484. [pdf] [code]
• Xiaozhi Wang, Ziqi Wang, Xu Han, Zhiyuan Liu, Juanzi Li, Peng Li, Maosong Sun, Jie Zhou, Xiang Ren. HMEAE: Hierarchical Modular Event Argument Extraction. Proceedings of EMNLP 2019, Hong Kong, China, pp. 5781–5787. [pdf] [code]
• Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou. FewRel 2.0: Towards More Challenging Few-Shot Relation Classification. Proceedings of EMNLP 2019, Hong Kong, China, pp. 6251–6256. [pdf] [code] [benchmark]
• Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, and Maosong Sun. DocRED: A Large-Scale Document-Level Relation Extraction Dataset. Proceedings of ACL 2019, Florence, Italy, pp. 764-777. [pdf] [code & data] [CodaLab]
• Fuli Luo, Peng Li, Pengcheng Yang, Jie Zhou, Yutong Tan, Baobao Chang, Zhifang Sui, and Xu Sun. Towards Fine-grained Text Sentiment Transfer. Proceedings of ACL 2019, Florence, Italy, 2019, pp. 2013-2022. [pdf] [code]
• Shuming Ma, Pengcheng Yang, Tianyu Liu, Peng Li, Jie Zhou, and Xu Sun. Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation. Proceedings of ACL 2019, Florence, Italy, pp. 2047-2057. [pdf] [code]
• Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, and Xu Sun. A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer. Proceedings of IJCAI 2019, Macao, China, pp. 5116-5122. [pdf] [code]
• Xiaozhi Wang, Xu Han, Zhiyuan Liu, Maosong Sun, and Peng Li. Adversarial Training for Weakly Supervised Event Detection. Proceedings of NAACL 2019, Minneapolis, Minnesota, pp. 998-1008. [pdf] [code]
• Deli Chen, Xiaoqian Liu, Yankai Lin, Peng Li, Jie Zhou, Qi Su, and Xu Sun. HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Networks. arXiv. 2019.
• Xu Han, Pengfei Yu, Zhiyuan Liu, Maosong Sun, and Peng Li. Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention. Proceedings of EMNLP 2018, Brussels, Belgium, pp. 2236-2245. [pdf] [code]
• Peng Li, Wei Li, Zhengyan He, Xuguang Wang, Ying Cao, Jie Zhou, and Wei Xu. Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering. arXiv. 2016. [code (in the directory "neural_qa", veryfied on Ubuntu 16.04 with PaddlePaddle 0.10.5)]
• Jie Zhou, Ying Cao, Xuguang Wang, Peng Li, and Wei Xu. Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation. Transactions of the Association for Computational Linguistics, 2016(4):371-383. [pdf]
• Peng Li, Yang Liu, Maosong Sun, Tatsuya Izuha, and Dakun Zhang. A Neural Reordering Model for Phrase-based Translation. Proceedings of COLING 2014, Dublin, Ireland, pp. 1897-1907. [pdf] [slides]
• Peng Li, Yang Liu, Maosong Sun. Recursive Autoencoders for ITG-based Translation. Proceedings of EMNLP 2013, Seattle, Washington, USA, pp. 567-577. [pdf] [Talk at MSRA Ph.D Forum]
• Peng Li, Yang Liu, Maosong Sun. An Extended GHKM Algorithm for Inducing Lambda-SCFG. Proceedings of AAAI-13, Bellevue, Washington, USA, pp. 605-611. [pdf] [slides]
• Peng Li, Yang Liu, Maosong Sun. A Beam Search Algorithm for ITG Word Alignment. Proceedings of COLING 2012, Mumbai, India, pp. 673-682. [pdf].
• Peng Li, Maosong Sun, Ping Xue. Fast-Champollion: A Fast and Robust Sentence Alignment Algorithm. Proceedings of COLING 2010: Posters, Beijing, China, pp. 710-718. [pdf]
• Xiance Si, Zhiyuan Liu, Peng Li, Qixia Jiang, Maosong Sun. Content-based and Graph-based Tag Suggestion. Proceedings of ECML/PKDD 2009 Discovery Challenge Workshop, Bled, Slovenia, pp. 243-260. [pdf]
• Zhiyuan Liu, Peng Li, Yabin Zheng, Maosong Sun. Clustering to Find Exemplar Terms for Keyphrase Extraction. Proceedings of EMNLP 2009, Singapore, 2009, pp. 257-266. [pdf]

Technical Reports

• Qiu Ran, Peng Li, Weiwei Hu, and Jie Zhou. Option Comparison Network for Multiple-choice Reading Comprehension. Technical Report, 2019. [pdf] [code]
• Zhiyuan Liu, Peng Li, Yabin Zheng, Maosong Sun. Community Detection by Affinity Propagation. Technical Report, 2008. [pdf]

Software

• str2vec is a toolkit for computing vector-space representations for variable-length phrases using recursive autoencoders (RAE). In this document, we demostrate
• How to train RAEs in an unsupervised and parallelized manner
• And how to compute vector-space representations for phrases once the RAE is trained
• hiero-decoder-py is a hierarchical phrase-based translation decoder which supports parallel decoding. New feature functions can also be implemented easily.

Professional Services

• NAACL: Reviewer (2018)
• ACM TIST: Reviewer (2015)
• EMNLP: Reviewer (2014)
• ACL: Reviewer (2014)
• The 5th Youth Workshop on Computational Linguistics (YWCL 2010): PC Chair

Education

• Aug, 2009 - Jan, 2015. Ph.D in Dept. of Computer Science and Technology, Tsinghua University, Beijing
• Aug, 2005 - Jul, 2009. B.S. in Dept. of Computer Science and Technology, Tsinghua University, Beijing