FANCHAO QI


I am a Ph.D. candidate in Department of Computer Science and Technology at Tsinghua University. I am advised by Professor Maosong Sun and affiliated with Natural Language Processing and Computational Social Science Lab (THUNLP). My research interests lie in the intersection of natural language processing and deep learning.

Experience

Ph.D. Candidate

Department of Computer Science and Technology,
Tsinghua University, Beijing, China.
August 2017 - Present

Undergraduate

Department of Electronic Engineering,
Tsinghua University, Beijing, China.
August 2013 - July 2017

High School

Taiyuan, Shanxi, China.
August 2010 - July 2013

Contact

  qifanchao1994 [at] gmail [dot] com
qfc17 [at] mails [dot] tsinghua [dot] edu [dot] cn
  Room 4-505, FIT Building, Tsinghua University, Beijing, China 100084
  GitHub
  Google Scholar
  LinkedIn

PUBLICATIONS

Conference Papers

  1. Fanchao Qi*, Yanhui Yang*, Jing Yi, Zhili Cheng, Zhiyuan Liu, Maosong Sun. QuoteR: A Benchmark of Quote Recommendation for Writing. Proceedings of The 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022). (Long Paper) [pdf] [code]
  2. Fanchao Qi*, Chuancheng Lv*, Zhiyuan Liu, Xiaojun Meng, Maosong Sun, Hai-Tao Zheng. Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information. Findings of the Association for Computational Linguistics: ACL 2022 (Findings of ACL: ACL 2022). (Long Paper) [pdf] [code]
  3. Yining Ye, Fanchao Qi, Zhiyuan Liu, Maosong Sun. Going "Deeper": Structured Sememe Prediction via Transformer with Tree Attention. Findings of the Association for Computational Linguistics: ACL 2022 (Findings of ACL: ACL 2022). (Long Paper) [pdf] [code]
  4. Fanchao Qi*, Yangyi Chen*, Xurui Zhang, Mukai Li, Zhiyuan Liu, Maosong Sun. Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer. Proceedings of The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021). (Long Paper) [pdf] [code]
  5. Fanchao Qi*, Yangyi Chen*, Mukai Li, Yuan Yao, Zhiyuan Liu, Maosong Sun. ONION: A Simple and Effective Defense Against Textual Backdoor Attacks. Proceedings of The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021). (Short Paper) [pdf] [code]
  6. Fanchao Qi*, Mukai Li*, Yangyi Chen*, Zhengyan Zhang, Zhiyuan Liu, Yasheng Wang, Maosong Sun. Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger. Proceedings of The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021). (Long Paper) [pdf] [code]
  7. Fanchao Qi*, Yuan Yao*, Sophia Xu*, Zhiyuan Liu and Maosong Sun. Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution. Proceedings of The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021). (Long Paper) [pdf] [code]
  8. Fanchao Qi, Yangyi Chen, Fengyu Wang, Zhiyuan Liu, Xiao Chen, Maosong Sun. Automatic Construction of Sememe Knowledge Bases via Dictionaries. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (Findings of ACL: ACL-IJCNLP 2021). (Long Paper) [pdf] [code]
  9. Chenglei Si, Zhengyan Zhang, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun. Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (Findings of ACL: ACL-IJCNLP 2021). (Short Paper) [pdf] [code]
  10. Guoyang Zeng*, Fanchao Qi*, Qianrui Zhou, Tingji Zhang, Zixian Ma, Bairu Hou, Yuan Zang, Zhiyuan Liu, Maosong Sun. OpenAttack: An Open-source Textual Adversarial Attack Toolkit. Proceedings of The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021). (Systems Demonstration) [pdf] [website]
  11. Huimin Chen, Yankai Lin, Fanchao Qi, Jinyi Hu, Peng Li, Jie Zhou, Maosong Sun. Aspect-Level Sentiment-Controllable Review Generation with Mutual Learning Framework. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-21). [pdf]
  12. Fanchao Qi*, Lei Zhang*, Yanhui Yang, Zhiyuan Liu, Maosong Sun. WantWords: An Open-source Online Reverse Dictionary System. Proceedings of 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020). (Systems Demonstration) [pdf] [code] [website]
  13. Yuan Zang*, Fanchao Qi*, Chenghao Yang*, Zhiyuan Liu, Meng Zhang, Qun Liu, Maosong Sun. Word-level Textual Adversarial Attacking as Combinatorial Optimization. Proceedings of The 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020). (Long Paper) [pdf] [code]
  14. Bairu Hou*, Fanchao Qi*, Yuan Zang*, Xurui Zhang, Zhiyuan Liu, Maosong Sun. Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet. Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020). (Short Paper) [pdf] [code]
  15. Fanchao Qi*, Liang Chang*, Maosong Sun, Sicong Ouyang, Zhiyuan Liu. Towards Building a Multilingual Sememe Knowledge Base: Predicting Sememes for BabelNet Synsets. Proceedings of The Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI-20). [pdf] [code]
  16. Lei Zhang*, Fanchao Qi*, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun. Multi-channel Reverse Dictionary Model. Proceedings of The Thirty-fourth AAAI Conference on Artificial Intelligence (AAAI-20). [pdf] [code]
  17. Fanchao Qi*, Junjie Huang*, Chenghao Yang, Zhiyuan Liu, Xiao Chen, Qun Liu, Maosong Sun. Modeling Semantic Compositionality with Sememe Knowledge. Proceedings of The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019). (Long Paper) [pdf] [code]
  18. Fanchao Qi, Yankai Lin, Maosong Sun, Hao Zhu, Ruobing Xie, Zhiyuan Liu. Cross-lingual Lexical Sememe Prediction. Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018). (Long Paper) [pdf] [code]

Journal Papers

  1. Fanchao Qi, Ruobin Xie, Yuan Zang, Zhiyuan Liu, Maosong Sun. Sememe Knowledge Computation: A Review of Recent Advances in Application and Expansion of Sememe Knowledge Bases. Frontiers of Computer Science, 2020, 15. [pdf]
  2. Zhengyan Zhang, Fanchao Qi, Zhiyuan Liu, Qun Liu, Maosong Sun. Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads. AI Open, 2021, 2:36-42. [pdf] [code]
  3. Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun. CPM: A Large-scale Generative Chinese Pre-trained Language Model. AI Open, 2021, 2:93-99. [pdf] [code]
  4. Huimin Chen, Zeyu Zhu, Fanchao Qi, Yining Ye, Zhiyuan Liu, Maosong Sun, Jianbin Jin. Country Image in COVID-19 Pandemic: A Case Study of China. IEEE Transactions on Big Data (TBD), 2020, 7(1):81-92 [pdf] [code]
  5. Yujia Qin*, Fanchao Qi*, Sicong Ouyang, Zhiyuan Liu, Cheng Yang, Yasheng Wang, Qun Liu, Maosong Sun. Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2020, 28:2364-2373 [pdf] [code]
  6. Yangguang Liu, Fanchao Qi, Zhiyuan Liu, Maosong Sun. Lexical Sememe Prediction by Dictionary Definitions and Local Semantic Correspondence. Research on Consistency Check of Sememe Annotations in HowNet, 35(4):23-34. (In Chinese) [pdf]
  7. Jiaju Du, Fanchao Qi, Maosong Sun, Zhiyuan Liu. Lexical Sememe Prediction by Dictionary Definitions and Local Semantic Correspondence. Journal of Chinese Information Processing, 34(5):1-9. (In Chinese) [pdf] [code]

Preprint

  1. Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Maosong Sun. SHUOWEN-JIEZI: Linguistically Informed Tokenizers For Chinese Language Model Pretraining. arXiv preprint arXiv:2106.00400. [pdf]
  2. Wenhao Li, Fanchao Qi, Maosong Sun, Xiaoyuan Yi, Jiarui Zhang. CCPM: A Chinese Classical Poetry Matching Dataset. arXiv preprint arXiv:01979. [pdf]
  3. Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Yasheng Wang, Xin Jiang, Zhiyuan Liu, Maosong Sun. Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks. arXiv preprint arXiv:2101.06969. [pdf]
  4. Yuan Zang, Bairu Hou, Fanchao Qi, Zhiyuan Liu, Xiaojun Meng, Maosong Sun. Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations. arXiv preprint arXiv:2009.09192. [pdf]
  5. Jiaju Du, Fanchao Qi, Maosong Sun. Using bert for word sense disambiguation. arXiv preprint arXiv:1909.08358. [pdf]
  6. Junjie Huang*, Fanchao Qi*, Chenghao Yang, Zhiyuan Liu, Maosong Sun. COS960: A Chinese word similarity dataset of 960 word pairs. arXiv preprint arXiv:1906.00247. [pdf]
  7. Fanchao Qi, Chenghao Yang, Zhiyuan Liu, Qiang Dong, Maosong Sun, Zhendong Dong. OpenHowNet: An open sememe-based lexical knowledge base. arXiv preprint arXiv:1901.09957. [pdf]

PROJECTS

OpenHowNet: An Open Sememe Knowledge Base

[paper] [API] [website]
A sememe is defined as the minimum semantic unit of human languages. HowNet is the most famous sememe knowledge base. It comprises more than 100,000 Chinese and English words and phrases that are manually annotated with a set of pre-defined sememes. Cooperating with the authors of HowNet, we release the core data of HowNet and develop an online sememe query website and a set of sememe access APIs.

WantWords: An Online Reverse Dictionary

[paper] [code] [website]
A reverse dictionary takes descriptions of words as input and outputs words semantically matching the input descriptions. Reverse dictionaries have great practical value such as solving the tip-of-the-tongue problem and helping new language learners. We present WantWords, a open-source online reverse dictionary, which not only significantly outperforms other reverse dictionary systems on English reverse dictionary performance, but also supports Chinese and English-Chinese as well as Chinese-English cross-lingual reverse dictionary queries for the first time.

OpenAttack: An Open-source Textual Adversarial Attack Toolkit

[paper] [code]
OpenAttack is an open-source textual adversarial attack toolkit. It currently builds in 14 typical attack models that cover all the attack types. Its highly inclusive modular design not only supports quick utilization of existing attack models, but also enables great flexibility and extensibility. It has broad uses including comparing and evaluating attack models, measuring robustness of a victim model, assisting in developing new attack models, and adversarial training.

TAADPapers: Must-read Papers on Textual Adversarial Attack and Defense

[website]
This is a reading list that records and organizes almost all the published papers about textual adversarial attack and defense.

SCpapers: Must-read Papers on Sememe Computation

[website]
This is a reading list that records and organizes almost all the published NLP papers about sememes and HowNet.