万瑶，于2019年12月获浙江大学计算机科学与技术专业博士学位，曾于2016年和2018年分别访问悉尼科技大学与伊利诺伊大学芝加哥分校。主要研究代码智能、自然语言处理、程序语言和人工智能。在软件工程和人工智能顶级会议／期刊上（合作）发表论文10余篇，包括ICSE、ASE、ACL、EMNLP、NAACL、AAAI、TOSEM、TSE等。首次发起了面向智能化编程的开源项目NaturalCC。相关研究获国家自然科学基金和腾讯犀牛鸟资助。个人主页：wanyao.me （欢迎感兴趣的学生进组实习！）。

Selected Publications

NaturalCC: An Open-Source Toolkit for Code Intelligence 

Yao Wan, Yang He, Zhangqian Bi, Jian-Guo Zhang, Yulei Sui, Hongyu Zhang, Kazuma Hashimoto, Hai Jin, Guandong Xu, Caiming Xiong, Philip S. Yu 
ICSE 2022 Demo Track. The 44th ACM/IEEE International Conference on Software Engineering, May 21–29, 2021, Pittsburgh, PA, USA. (CCF A)

What Do They Capture? - A Structural Analysis of Pre-Trained Language Models for Source Code 
Yao Wan, Wei Zhao, Hongyu Zhang, Yulei Sui, Guandong Xu and Hai Jin 
ICSE 2022. The 44th ACM/IEEE International Conference on Software Engineering, May 21–29, 2021, Pittsburgh, PA, USA. (CCF A)

Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization 
Juncai Guo, Jin Liu, Yao Wan, Li Li, Pingyi Zhou 
ACL 2022. The 60th Annual Meeting of the Association for Computational Linguistics (CCF A)

Compilable Neural Code Generation with Compiler Feedback 
Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, jin liu, hao wu, Xin Jiang, Qun Liu 
Findings of ACL 2022. The 60th Annual Meeting of the Association for Computational Linguistics (CCF A)

DANets: Deep Abstract Networks for Tabular Data Processing 
Jintai Chen, KuanLun Liao, Yao Wan, Danny Chen, Jian Wu 
AAAI 2022. The 36th AAAI Conference on Artificial Intelligence (CCF A)

XCode: Towards Cross-Language Code Representation with Large-Scale Pre-Training 
Zehao Lin, Guodun Li, Jingfeng Zhang, Yue Deng, Xiangji Zeng, Yin Zhang, Yao Wan 
TOSEM 2021. ACM Transactions on Software Engineering and Methodology (CCF A)

Fix-Filter-Fix: Intuitively Connect Any Models for Effective Multi-task Bug Fixing 
Haiwen Hong, Jingfeng Zhang, Yin Zhang, Yao Wan and Yulei Sui 
EMNLP 2021. The 2021 Conference on Empirical Methods in Natural Language Processing (CCF B)

Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots 
Wenting Zhao, Ye Liu, Yao Wan and Philip Yu 
Findings of EMNLP 2021. The 2021 Conference on Empirical Methods in Natural Language Processing (CCF B)

HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization 
Ye Liu, Jianguo Zhang, Yao Wan, Congying Xia, Lifang He and Philip Yu 
EMNLP 2021 (Short Paper). The 2021 Conference on Empirical Methods in Natural Language Processing (CCF B)

Disentangled Code Representation Learning for Multiple Programming Languages 
Jingfeng Zhang, Haiwen Hong, Yin Zhang, Yao Wan, Ye Liu, Yulei Sui 
Findings of ACL 2021. The 59th Annual Meeting of the Association for Computational Linguistics (CCF A)

KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning 
Ye Liu, Yao Wan, Lifang He, Hao Peng, Philip S. Yu 
AAAI 2021. The 35th AAAI Conference on Artificial Intelligence (CCF A)

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference 
Jianguo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip S. Yu, Richard Socher and Caiming Xiong 
EMNLP 2020. The 2020 Conference on Empirical Methods in Natural Language Processing (CCF B)

Reinforcement-Learning-Guided Source Code Summarization via Hierarchical Attention
Wenhua Wang, Yuqun Zhang, Yulei Sui, Yao Wan, Zhou Zhao, Jian Wu, Philip S. Yu, Guandong Xu
TSE 2020. IEEE Transaction on Software Engineering (CCF A)

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce 
Jian-Guo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu 
NAACL-HLT 2019. The 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, June 2-7, 2019, Minneapolis, USA. (CCF C)

Multi-Modal Attention Network Learning for Semantic Source Code Retrieval
Yao Wan, Jingdong Shu, Yulei Sui, Guandong Xu, Zhou Zhao, Jian Wu, Philip S. Yu
ASE 2019. The 34th ACM/IEEE International Conference on Automated Software Engineering, November 11–15, 2019, San Diego, United States. ACM, New York, NY, USA. (CCF A)

Improving Automatic Source Code Summarization via Deep Reinforcement Learning
Yao Wan, Zhou Zhao, Min Yang, Guandong Xu, Haochao Ying, Jian Wu, Philip S. Yu
ASE 2018. The 33rd ACM/IEEE International Conference on Automated Software Engineering, September 3–7, 2018, Montpellier, France. (CCF A)

Program Committee Member

ACL: 2022,2021; EMNLP: 2021; AAAI: 2022,2021; IJCAI: 2021; SIGKDD: 2022; WSDM: 2022; COLING: 2020; NLPCC: 2020