About me

I am currently an Algorithm Engineer at the Search Algorithm Team in Alibaba, Hangzhou. Before that, I was a member of THUCoAI group and received my M.S. degree from Department of Computer Science and Technology in Tsinghua University, Beijing, under supervision of Prof. Minlie Huang. My major research interests are about dialog systems, search engines and reinforcement learning.

Education

  • Aug. 2019 - Jun. 2021 M.S., Department of Computer Science and Technology, Tsinghua University, Beijing, China.
  • Sep. 2015 - Jul. 2019 B.S., Department of Computer Science and Technology, Tsinghua University, Beijing, China.

Publications

(* indicates equal contribution)

Preprint

  • Silin Gao, Ryuichi Takanobu and Minlie Huang. End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management. [pdf] [bib]

Conference Paper

  • Ryuichi Takanobu*, Wenchang Ma* and Minlie Huang. CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation. (Oral) The 26th Conference on Empirical Methods in Natural Language Processing. (EMNLP’21) [pdf] [bib] [code]
  • Ting Han, Ximing Liu, Ryuichi Takanobu, Yixin Lian, Chongxuan Huang, Dazhen Wan, Wei Peng and Minlie Huang. MultiWOZ 2.3: A Multi-Domain Task-Oriented Dialogue Dataset Enhanced with Annotation Corrections and Co-reference Annotation. The 10th CCF International Conference on Natural Language Processing and Chinese Computing. (NLPCC’21) [pdf] [bib] [data]
  • Ryuichi Takanobu*, Jiexi Liu*, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng and Minlie Huang. Robustness Testing of Language Understanding in Task-Oriented Dialog. (Oral) The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. (ACL-IJCNLP’21) [pdf] [bib] [code]
  • Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun and Jie Zhou. ERICA: Improving Entity and Relation Understanding for Pretrained Language Models by Contrastive Learning. (Oral) The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. (ACL-IJCNLP’21) [pdf] [bib] [code]
  • Ryuichi Takanobu*, Silin Gao*, Wei Peng, Qun Liu and Minlie Huang. HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management. The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Findings. (ACL-IJCNLP’21 Findings) [pdf] [bib] [code]
  • Peixin Huang, Xiang Zhao, Ryuichi Takanobu, Zhen Tan and Weidong Xiao. Joint Event Extraction with Hierarchical Policy Network. The 28th International Conference on Computational Linguistics. (COLING’20) [pdf] [bib]
  • Ryuichi Takanobu, Runze Liang and Minlie Huang. Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition. The 58th Annual Meeting of the Association for Computational Linguistics. (ACL’20) [pdf] [bib] [code]
  • Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu and Minlie Huang. ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems. (Demo) The 58th Annual Meeting of the Association for Computational Linguistics. (ACL’20) [pdf] [bib] [code]
  • Ryuichi Takanobu, Qi Zhu, Jinchao Li, Baolin Peng, Jianfeng Gao and Minlie Huang. Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation. (Best Paper) The 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue. (SIGDIAL’20) [pdf] [bib]
  • Ryuichi Takanobu, Hanlin Zhu and Minlie Huang. Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog. (Oral) The 24th Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. (EMNLP-IJCNLP’19) [pdf] [bib] [code]
  • Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang and Jianfeng Gao. ConvLab: Multi-Domain End-to-End Dialog System Platform. (Demo, Best Demo Paper Nominee) The 57th Annual Meeting of the Association for Computational Linguistics. (ACL’19) [pdf] [bib] [code]
  • Ryuichi Takanobu, Tao Zhuang, Minlie Huang, Jun Feng, Haihong Tang and Bo Zheng. Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning. The 28th International Conference on World Wide Web. (WWW’19) [pdf] [bib]
  • Ryuichi Takanobu*, Tianyang Zhang*, Jiexi Liu and Minlie Huang. A Hierarchical Framework for Relation Extraction with Reinforcement Learning. (Oral) The 33rd AAAI Conference on Artificial Intelligence. (AAAI’19) [pdf] [bib] [code]
  • Ryuichi Takanobu, Minlie Huang, Zhongzhou Zhao, Fenglin Li, Haiqing Chen, Liqiang Nie and Xiaoyan Zhu. Weakly Supervised Topic Segmentation and Labeling in Goal-Oriented Dialogues via Reinforcement Learning. The 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence. (IJCAI-ECAI’18) [pdf] [bib] [code]

Journal Paper

  • Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang and Xiaoyan Zhu. Recent Advances and Challenges in Task-Oriented Dialog Systems. Science China Technological Sciences, 2020. (SCTS’20) [pdf] [bib]
  • Lizi Liao, Ryuichi Takanobu, Yunshan Ma, Xun Yang, Minlie Huang and Tat-Seng Chua. Topic-Guided Conversational Recommender in Multiple Domains. Transactions on Knowledge and Data Engineering, 2020. (TKDE’20) [pdf] [bib] [code]

Workshop Paper

  • Runze Liang, Ryuichi Takanobu, Fenglin Li, Ji Zhang, Haiqing Chen and Minlie Huang. Turn-Level User Satisfaction Estimation in E-commerce Customer Service. The 4th Workshop on e-Commerce and NLP at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. (ECNLP4@ACL-IJCNLP’21) [pdf] [bib]
  • Jinchao Li*, Qi Zhu*, Lingxiao Luo, Lars Liden, Kaili Huang, Shahin Shayandeh, Runze Liang, Baolin Peng, Zheng Zhang, Swadheen Shukla, Ryuichi Takanobu, Minlie Huang and Jianfeng Gao. Multi-Domain Task Completion Dialog Challenge II at DSTC9. The 9th Dialog System Technology Challenge Workshop at the 35th AAAI Conference on Artificial Intelligence. (DSTC9@AAAI’21) [pdf] [bib]
  • Jinchao Li, Baolin Peng, Sungjin Lee, Jianfeng Gao, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Hannes Schulz, Adam Atkinson and Mahmoud Adada. Multi-Domain Task-Completion Dialog Challenge at DSTC8. The 8th Dialog System Technology Challenge Workshop at the 34th AAAI Conference on Artificial Intelligence. (DSTC8@AAAI’20) [pdf] [bib]

Experience

  • Aug. 2021 - present. Senior Algorithm Engineer, Search Algorithm Team, Alibaba, Hangzhou, China.
  • Feb. 2021 - May 2021. Applied Scientist Intern, Alexa AI Team, Amazon, Seattle, WA, US.
  • Jun. 2020 - Sep. 2020. Research Intern, WeChat AI Team, Tencent, Beijing, China.
  • Jun. 2018 - Sep. 2018. Research Intern, Search Algorithm Team, Alibaba, Hangzhou, China.

Services

  • Organizer: DSTC 8 Track 1, DSTC 9 Track 2
  • PC Member: ACL’20/21, EMNLP’20/21, EACL’21, NAACL’21, DialDoc’21, NLP4Conv’21
  • Review Assistant: IJCAI’19, EMNLP’19

Honors and Awards

  • Outstanding Master Thesis, Tsinghua University, 2021 (Top-1 score in the DCST)
  • Outstanding Master Graduate, Tsinghua University, 2021
  • SIGDIAL Best Paper, 2020
  • Alibaba Innovative Research Award, 2019
  • ACL Best Demo Paper Nominee, 2019
  • Outstanding Undergraduate Thesis, Beijing, 2019 (Top-1 score in the DCST)
  • Outstanding Undergraduate, Department of Computer Science and Technology, Tsinghua University, 2019
  • Sensetime Scholarship, 2018
  • Qualcomm Scholarship, 2018
  • Chinese Mathematical Olympiad (CMO), Second Prize, 2015