Ao Liu

Ao Liu

Tokyo Institute of Technology

Hello, I am Ao Liu (刘傲， リュウ　アオ), a final-year Ph.D. student at Tokyo Institute of Technology.

My research interest includes natural language generation, semi-supervised learning and pretrained language models.

🔥 News

  • 2023.05:  🎉🎉 A paper accepted at *SEM 2023.
  • 2022.12:  🎉🎉 A paper accepted at Journal of Information Processing.
  • 2022.11:  🎉🎉 Finished my internship at IBM Research Tokyo.
  • 2022.10:  🎉🎉 A long paper accepted at EMNLP 2022.

📖 Educations

  • 2020.09 - 2023.09, doctoral student in the Department of Computer Science of Tokyo Institute of Technology, advised by Prof. Naoaki Okazaki.
  • 2017.09 - 2020.06, master student in the School of Computer Science and Engineering of UESTC, advised by Prof. Zenglin Xu.
  • 2013.09 - 2017.06, undergraduate student in the School of Information and Communication Engineering of University of Electronic Science and Technology of China (UESTC), advised by Prof. Zenglin Xu.
  • 2015.09 - 2016.08, exchange student in the JUSST program of the University of Electro-Communications, advised by Prof. Hisashi Koga.

💼 Internships

  • 2022.08 - 2022.11, IBM Research Tokyo, advised by Yang Zhao.
  • 2021.11 - 2022.06, Microsoft Research Asia, advised by Haoyu Dong.

📝 Preprints

  • Towards Effective Multi-Task Interaction for Entity-Relation Extraction: A Unified Framework with Selection Recurrent Network. [paper]. An Wang, Ao Liu, Hieu Hanh Le and Haruo Yokota.

📝 Publications

  • Generative Data Augmentation for Aspect Sentiment Quad Prediction. An Wang, Junfeng Jiang, Youmi Ma, Ao Liu, and Naoaki Okazaki. In Proceedings of *SEM 2023: The 12th Joint Conference on Lexical and Computational Semantics (StarSEM), pages (to appear), Toronto, Canada, July 2023.
  • Improving Logical-level Natural Language Generation with Topic-conditioned Data Augmentation and Logical Form Generation. [paper]. Ao Liu, Congjian Luo, Naoaki Okazaki. Journal of Information Processing, May 2023.
  • PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation. [paper]; [code]. Ao Liu, Haoyu Dong, Naoaki Okazaki, Shi Han, Dongmei Zhang. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022).
  • Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction. [paper]; [code]. Yidong Wang, Hao Wu, Ao Liu, Wenxin Hou, Zhen Wu, Jindong Wang, Takahiro Shinozaki, Manabu Okumura, Yue Zhang. International Conference on Computational Linguistics 2022 (COLING 2022).
  • A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks. [paper]. Yu Pan, Zeyong Su, Ao Liu, Wang J Q, Nannan Li, Zenglin Xu. Thirty-ninth International Conference on Machine Learning (ICML 2022).
  • Table Pretraining: A Survey on Model Architectures, Pretraining Objectives, and Downstream Tasks. [paper]. Haoyu Dong, Zhoujun Cheng, Xinyi He, Mengyu Zhou, Anda Zhou, Fan Zhou, Ao Liu, Shi Han and Dongmei Zhang. The 31st International Joint Conference on Artificial Intelligence. (IJCAI-ECAI 2022, Survey Track).
  • Semi-Supervised Formality Style Transfer with Consistency Training [paper]; [code]. Ao Liu, An Wang, Naoaki Okazaki. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022).
  • Multi-Level Multimodal Transformer Network for Multi-Modal Recipe Comprehension. [paper]. Ao Liu, Shuai Yuan, Chenbin Zhang, Congjian Luo, Yaqing Liao, Zenglin Xu. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (short) (SIGIR 2020).
  • Improving Contextual Language Models for Response Retrieval in Multi-Turn Conversation. [paper]. Junyu Lu, Xiancong Ren, Yazhou Ren, Ao Liu, Zenglin Xu. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (short) (SIGIR 2020).
  • Read, Attend, and Exclude: Multi-Choice Reading Comprehension by Mimicking Human Reasoning Process. [paper]. Chenbin Zhang, Congjian Luo, Junyu Lu, Ao Liu, Bing Bai, Kun Bai and Zenglin Xu. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (short) (SIGIR 2020).
  • Machine Reading Comprehension: Matching and Orders. [paper]; [code]. Ao Liu, Lizhen Qu, Junyu Lu, Chenbin Zhang, Zenglin Xu. Proceedings of the 28th ACM International Conference on Information and Knowledge Management (short) (CIKM 2019).

🎖 Honors and Awards

  • Stars of Tomorrow, Microsoft Research Asia, 2022.
  • Tokyo Tech Advanced Human Resource Development Fellowship for Doctoral Students, Tokyo Institute of Technology, 2021-2023 (Scholarship 1,800,000 JPY/year, Research Funds 300,000 JPY/year)
  • Tsubame Scholarship, Tokyo Institue of Technology, 2020.
  • SIGIR Student Travel Grants: SIGIR2020, CIKM2019.

💬 Invited Talks

  • 2022.08, Table-to-Logic Pretraining for Logical Table-to-Text Generation. Invited talk at Knowledge and Information Research Team，National Institute of Advanced Industrial Science and Technology (AIST).

📄 Academic Services

  • Reviewer for Conferences: ICML (2022, 2023), NeurIPS 2022, EMNLP 2022, ACL 2023.