Boyuan Pan (潘博远)

I'm a fifth-year Ph.D. student in the State Key Lab of CAD&CG at Zhejiang University in China. My advisors are Prof. Xiaofei He and Prof. Deng Cai. During my Ph.D. career, I was a visiting scholar at UIUC (working with Prof. Bo Li) and OSU (working with Prof. Huan Sun).

My research interests fall in the general areas and applications of machine learning and natural language processing (NLP), especially the recent developments in transfer learning, reinforcement learning and adversarial learning to work towards the goal of the combination of language understanding and generation.

News

• Jan 2021

  • Our paper "Self-Supervised Attention Flow for Dialogue State Tracking" got accepted in Neurocomputing.

• September 2020

  • Our paper "T3: Tree-Autoencoder Regularized Adversarial Text Generation for Targeted Attack" got accepted in EMNLP 2020.

• June 2020

  • Our paper "Adversarial Mutual Information for Text Generation" got accepted in ICML 2020, Vienna, Austria.

• Jan 2020

  • Our paper "Bi-Decoder Augmented Network for Neural Machine Translation" got accepted in Neurocomputing.

• October 2019

  • I am excited to visit the University of Illinois at Urbana-Champaign and work with Prof. Bo Li!

• June 2019

  • I'm excited to join the Alibaba DAMO Academy as a research intern!

• May 2019

  • Our paper "Reinforced Dynamic Reasoning for Conversational Question Generation" got accepted in ACL 2019, Florence, Italy.

• November 2018

  • I am excited to visit the Ohio State University and work with Prof. Huan Sun!

  • Our work in NeurIPS 2018 was invited to have a talk on the 16th China Symposium on Machine Learning Applications (MLA 2018), Nanjing, China.

• September 2018

  • Our paper "MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models" got accepted in NeurIPS 2018, Montreal, Canada.

• May 2018

  • Our work in ACL 2018 was invited to present on The Third SFU-ZJU Joint Symposium on Big Data and Visual Computing, Hangzhou, China.

• April 2018

  • Our paper "Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference" got accepted in ACL 2018 (oral), Melbourne, Australia.

• May 2017

  • Our Model "MEMEN" achieved the second place on the SQuAD leaderboard!

• April 2017

  • Our paper "Robust Asymmetric Bayesian Adaptive Matrix Factorization" got accepted in IJCAI 2017, Melbourne, Australia.

Publications

2021

• Self-Supervised Attention Flow for Dialogue State Tracking

  Boyuan Pan*, Yazheng Yang*, Bo Li, Deng Cai

  Neurocomputing

  [paper]

2020

• T3: Tree-Autoencoder Regularized Adversarial Text Generation for Targeted Attack

  Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li

  The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)

  [paper] [code]

• Adversarial Mutual Information for Text Generation

  Boyuan Pan*, Yazheng Yang*, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-sheng Hua, Deng Cai, Bo Li

  Thirty-seventh International Conference on Machine Learning (ICML 2020)

  [paper] [code]

• Towards Evaluating the Robustness of Chinese BERT Classifiers

  Boxin Wang, Boyuan Pan, Xin Li, Bo Li

  arXiv preprint arXiv:2004.03742

  [paper]

• Bi-Decoder Augmented Network for Neural Machine Translation

  Boyuan Pan, Yazheng Yang, Zhou Zhao, Yueting zhuang, Deng Cai

  Neurocomputing

  [paper]

2019

• Discriminate and Reconstruct: Learning from Language Model to Answer Keyword Questions

  Boyuan Pan, Yazheng Yang, Yueting Zhuang, Deng Cai

  The second China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI 2019) (oral)

  [paper]

• Reinforced Dynamic Reasoning for Conversational Question Generation

  Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun

  Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)

  [paper] [code]

2018

• MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models

  Boyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He

  Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018)

  [paper] [poster]

• Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference

  Boyuan Pan, Yazheng Yang, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He

  Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) (oral)

  [paper] [code] [slides]

2017

• Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation

  Boyuan Pan, Hao Li, Zhou Zhao, Deng Cai, Xiaofei He

  arXiv preprint arXiv:1711.00179

  [paper]

• MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension

  Boyuan Pan, Hao Li, Zhou Zhao, Bin Cao, Deng Cai, Xiaofei He

  arXiv preprint arXiv:1707.09098

  [paper]

• Robust Asymmetric Bayesian Adaptive Matrix Factorization

  Xin Guo, Boyuan Pan, Deng Cai, Xiaofei He

  Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI 2017)

  [paper]

Education

• 2016/09 - present

  • Ph.D. in Computer Science and Technology, Zhejiang University.

• 2012/09 - 2016/06

  • B.S. in Mathematical Science, Zhejiang University.

• 2014/08 - 2014/09

  • Summer School, University of California, Los Angeles (UCLA).

Experiences

• 2019/09 - 2020/08

  • Visiting Scholar at University of Illinois at Urbana-Champaign (UIUC), Urbana, USA.

• 2019/06 - 2019/09

  • Research Intern at Alibaba DAMO Academy, Hangzhou, China.

• 2018/11 - 2019/05

  • Visiting Scholar at Ohio State University (OSU), Columbus, USA.

• 2016/11 - 2017/09

  • Research Intern at Eigen Technologies, Hangzhou, China.

Professional Services

Program Committee Member: AAAI (2018), NeurIPS (2019), ACL (2018, 2019, 2020), EMNLP (2020), NAACL (2021).

Journal Reviewer: IEEE TNNLS.

---