Quan Liu, PhD. 刘权  (How to pronounce?)

Principal Researcher, State Key Laboratory of Cognitive Intelligence, China
Research Scientist, Deputy Dean of iFLYTEK Research, Hefei, China
No.666, West Wangjiang Road, Hefei, China

Natural language processing is so interesting and I have been working in this field for 9 years. In 2016, the system constructed by us ranked 1st at the Winograd Schema Challenge (see wiki), a recent commonsense reasoning task held in IJCAI 2016, New York City, USA (NYU; MIT Technology Review; Nuance; IEEE Spectrum). Details for describing our Neural Association Model are available at here. In 2018, the system constructed by us ranked 1st at the end-to-end speech translation track of IWSLT 2018.

Research works: Machine Learning for Natural Language Processing & AI, (2011~present)

• Commonsense Reasoning via Deep Learning
  Research in commonsense reasoning, neural-symbolic computing, etc.

• Semantic Representation for NLPs
  Represent natural language using neural network methods.

• Spoken Dialogue System
  Research in spoken language understanding, question answering and dialog management.

• Multi-modal human-computer interaction
  Research in Multi-modal human-computer interaction.

Some highlights

• 2020, one paper working on dialogue disentanglement has been accepted by IJCAI 2020. [paper]

• 2020, one paper working on table fact verification has been accepted by EMNLP 2020. [paper]

• 2020, one paper working on multi-turn chatbots has been accepted by CIKM 2020. [paper]

• 2020, one paper working on sentence generation has been accepted by Computer Speech & Language, 2020. [paper]

• 2020, one paper working on neural sybomlic reasoning has been accepted by COLING 2020.

• 2019, one paper working on retrieval-based chatbots has been accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019. [paper]

• 2019, two papers working on dialogue response selection have been accepted by EMNLP 2019 [paper] and CIKM 2019 [paper].

• 2019, one paper working on sentence generation has been accepted by ICASSP 2019. [paper]

• 2018, we participated in IWSLT end-to-end speech translation track and won the first place. [paper]

• 2017, the undergraduate student I supervised in Canada, Andrew Evdokimov, has got an offer from Google in Mountain View at the Spring of 2017.

• 2017, one paper working on commonsense reasoning has been accepted by IJCAI 2017. [paper]

• 2016, we participated in Winograd Schema Challenge and won the first place. [link]

• 2015, one paper working on semantic representation has been accepted by ACL 2015. [paper]

Publications

• Hui Liu, Zhan Shi, Jia-Chen Gu, Quan Liu, Si Wei, Xiaodan Zhu. End-to-End Transition-Based Online Dialogue Disentanglement. International Joint Conference on Artificial Intelligence (IJCAI) 2020. [pdf]

• Xiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu, Zhigang Chen and Xiaodan Zhu. Program Enhanced Fact Verification with Verbalization and Graph Attention Network. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. [pdf]

• Jia-Chen Gu, Tianda Li, Quan Liu, Zhen-Hua Ling, Zhiming Su, Si Wei, Xiaodan Zhu. Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots. The 29th ACM International Conference on Information and Knowledge Management (CIKM) 2020. [pdf]

• Yufei Feng, Zi'ou Zheng, Quan Liu, Michael Greenspan and Xiaodan Zhu. Exploring End-to-End Differentiable Natural Logic Modeling. The 28th International Conference on Computational Linguistics (COLING) 2020.

• Yu-Ping Ruan, Zhen-Hua Ling, Xiaodan Zhu, Quan Liu, Jia-Chen Gu. Generating Diverse Conversation Responses by Creating and Ranking Multiple Candidates. Computer Speech & Language, 2020, 62:101071. [pdf]

• Jia-Chen Gu, Tianda Li, Quan Liu, Xiaodan Zhu, Zhen-Hua Ling, Yu-Ping Ruan. Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems. AAAI 2020 Workshop on DSTC8, New York, USA.

• Yu-Ping Ruan, Zhen-Hua Ling, Jia-Chen Gu, Quan Liu. Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking. AAAI 2020 Workshop on DSTC8, New York, USA.

• Jia-Chen Gu, Zhen-Hua Ling, Quan Liu. Utterance-to-utterance Interactive Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019, 28:369-379. [pdf]

• Jia-Chen Gu, Zhen-Hua Ling, Xiaodan Zhu, Quan Liu. Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019, Hong Kong, China. [pdf]

• Jia-Chen Gu, Zhen-Hua Ling, Quan Liu. Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots. The 28th ACM International Conference on Information and Knowledge Management (CIKM) 2019, Beijing, China. [pdf]

• Yu-Ping Ruan, Zhen-Hua Ling, Quan Liu, Zhi-Gang Chen, Nitin Indurkhya. Condition-Transforming Varitional Autoencoder for Conversation Response Generation. International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019. [pdf]

• Yu-Ping Ruan, Zhen-Hua Ling, Quan Liu, Jia-Chen Gu, Xiaodan Zhu. Promoting Diversity for End-to-End Conversation Response Generation. AAAI 2019 Workshop on DSTC7, Honolulu, Hawaii, USA. [pdf]

• Jia-Chen Gu, Zhen-Hua Ling, Yu-Ping Ruan, Quan Liu. Building Sequential Inference Models for End-to-End Response Selection. AAAI 2019 Workshop on DSTC7, Honolulu, Hawaii, USA. [website] [pdf]

• Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong, Zhiqiang Ma, Rui Song, Chongliang Wu, Quan Liu. The USTC-NEL Speech Translation system at IWSLT 2018. International Workshop on Spoken Language Translation (IWSLT) 2018, Bruges, Belgium. [pdf]

• Joseph Sanu, Mingbin Xu, Hui Jiang, Quan Liu. Word Embeddings based on Fixed-Size Ordinally Forgetting Encoding. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2017, Copenhagen, Denmark. [pdf]

• Quan Liu, Hui Jiang, Andrew Evdokimov, Zhen-Hua Ling, Xiaodan Zhu, Si Wei, Yu Hu. Cause-Effect Knowledge Acquisition and Neural Association Model for Solving A Set of Winograd Schema Problems. International Joint Conference on Artificial Intelligence (IJCAI) 2017, Melbourne, Australia, July 2017. [pdf]

• Quan Liu, Hui Jiang, Zhen-Hua Ling, Xiaodan Zhu, Si Wei, Yu Hu. Combing Context and Commonsense Knowledge Through Neural Networks for Solving Winograd Schema Problems. AAAI Spring Symposium, Stanford, Palo Alto, U.S.A, March 2017. [pdf][slides]

• Quan Liu, Hui Jiang, Zhen-Hua Ling, Si Wei, Yu Hu. Probabilistic Reasoning via Deep Learning: Neural Association Models. IJCAI 2016 Workshop on Deep Learning for Artificial Intelligence (DLAI). New York, U.S.A, July, 2016. [pdf] [slides]

• Quan Liu, Wu Guo, Zhen-Hua Ling, Hui Jiang, Yu Hu. Intra-Topic Variability Normalization based on Linear Projection for Topic Classification. North American Chapter of the Association for Computational Linguistics (NAACL) 2016, San Diego, U.S.A, June, 2016. [pdf]

• Quan Liu, Zhen-Hua Ling, Hui Jiang, Yu Hu. Part-of-Speech Relevance Weights for Learning Word Embeddings. arXiv, 2016. [pdf]

• Quan Liu, Hui Jiang, Si Wei, Zhen-Hua Ling, Yu Hu. Learning Semantic Word Embeddings based on Ordinal Knowledge Constraints. Annual Meeting of the Association for Computational Linguistics (ACL) 2015, Beijing, China, July, 2015. [pdf] [toolkit]

• Quan Liu, Wu Guo, Zhen-Hua Ling. Integrate Document Ranking Information into Confidence Measure Calculation for Spoken Term Detection. arXiv, 2015. [pdf]

Awards and honors

• Outstanding Graduates (PhD) of University of Science and Technology of China, 2017, China.

• Best Internship Award of iFLYTEK Research 2014. Hefei, China.

• Best Student Paper Award of National Conference on Man-Machine Speech Communication 2013. Guiyang, China.

• National Undergraduate Scholarship 2009. Awarded by Ministry of Education, China.