Xuefeng Bai

Xuefeng Bai

Ph.D candidate

ZheJiang University

Biography

I am currently a forth (last) year PhD student at Zhejiang University, where I’m honored to be advised by Yue Zhang. Previously, I earned my master degree from the Harbin Institute of Technology, working with Hailong Cao and Tiejun Zhao. I received my undergraduate degree on Computer Science from Harbin Institute of Technology. I also worked (as research intern) with Sougou, Alibaba DAMO Academy and Tencent AI Lab.

My research area spans from fundamental language analysis (semantics in particular) to real-world NLP applications (e.g., dialogue systems, text generation, translation).

Download my resumé.

Interests
  • Natural Language Processing
  • Semantics
  • Dialogues
  • Generation
Education

  • PhD in Computer Science, 2023 (expected)

    Zhejiang University

  • MEng in Computer Science, 2019

    Harbin Institute of Technology

  • BEng in Computer Science, 2017

    Harbin Institute of Technology

Recent News

One paper was accepted by EMNLP2022
EMNLP2022 Oct 2022
Our paper “Cross-domain Generalization for AMR Parsing” was accepted by EMNLP2022.
One paper was accepted by COLING2022
COLING2022 Aug 2022
Our paper “Semantic-based Pre-training for Dialogue Understanding” was accepted as oral in COLING2022.
One paper was accepted by INLG2022
INLG2022 May 2022
Our paper “The Cross-lingual Conversation Summarization Challenge” was accepted as oral in INLG2022 conference.
One paper was accepted by ACL2022
ACL2022 Feb 2022
Our paper “Graph Pre-training for AMR Parsing and Generation” was accepted as poster in ACL2022 main conference.
Starting to use hugo academic blogs.
Jan 2021
The old website was deprecated and I will update information on this one.

Recent Posts

Welcome to Wowchemy, the website builder for Hugo
Welcome 👋 We know that first impressions are important, so we’ve populated your new site with some initial content to help you get familiar with everything in no time.
Xuefeng Bai
Dec 13, 2020 3 min read 教程
Welcome to Wowchemy, the website builder for Hugo

Featured Publications

Xuefeng Bai, Yulong Chen, Yue Zhang
January, 2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), (ACL,CCF-A), Dublin, Ireland, May 22-27, 2022
Graph Pre-training for AMR Parsing and Generation

Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However, PLMs are typically pre-trained on textual data, thus are sub-optimal for modeling structural knowledge. To this end, we investigate graph self-supervised training to improve the structure awareness of PLMs over AMR graphs. In particular, we introduce two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-training. We further design a unified framework to bridge the gap between pre-training and fine-tuning tasks. Experiments on both AMR parsing and AMR-to-text generation show the superiority of our model. To our knowledge, we are the first to consider pre-training on semantic graphs.
Cite DOI URL

Recent Publications

Quickly discover relevant content by filtering publications.
Xuefeng Bai, Linfeng Song, Yue Zhang (2022). Semantic-based Pre-training for Dialogue Understanding. In Proceedings of the 29th International Conference on Computational Linguistics (COLING, CCF-B), Gyeongju, Korea, October 12-17, 2022.

Xuefeng Bai, Yulong Chen, Yue Zhang (2022). Graph Pre-training for AMR Parsing and Generation. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), (ACL,CCF-A), Dublin, Ireland, May 22-27, 2022.

Cite DOI URL

Yulong Chen, Ming Zhong, Xuefeng Bai, Naihao Deng, Jing Li, Xianchao Zhu, Yue Zhang (2022). The Cross-lingual Conversation Summarization Challenge. Proceedings of the 15th International Natural Language Generation Conference, (INLG), Waterville, American, July 18-22, 2022.

Cite URL

Xuefeng Bai, Pengbo Liu, Yue Zhang (2021). Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP, SCI-Q1, JCR-Q1).

Cite DOI URL

Xuefeng Bai, Yulong Chen, Linfeng Song, Yue Zhang (2021). Semantic Representation for Dialogue Modeling. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, (ACL/IJCNLP, CCF-A), (Volume 1: Long Papers), Virtual Event, August 1-6, 2021.

Cite DOI URL

Xuefeng Bai, Yafu Li, Zhirui Zhang, Mingzhou Xu, Boxing Chen, Weihua Luo, Derek F. Wong, Yue Zhang (2021). Sentence-State LSTMs For Sequence-to-Sequence Learning. Natural Language Processing and Chinese Computing - 10th CCF International Conference, (NLPCC, CCF-C), Qingdao, China, October 13-17, 2021, Proceedings, Part I.

Cite DOI URL

Xuefeng Bai, Linfeng Song, Yue Zhang (2020). Online Back-Parsing for AMR-to-Text Generation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, (EMNLP, CCF-B), Online, November 16-20, 2020.

Cite DOI URL

Xuefeng Bai, Hailong Cao, Kehai Chen, Tiejun Zhao (2019). A Bilingual Adversarial Autoencoder for Unsupervised Bilingual Lexicon Induction. IEEE ACM Transaction on Audio, Speech, and Language Processing (TASLP, SCI-Q1, JCR-Q1).

Cite DOI URL

Xuefeng Bai, Yue Zhang, Hailong Cao, Tiejun Zhao (2019). Duality Regularization for Unsupervised Bilingual Lexicon Induction. Arxiv Preprint.

Cite URL

Xuefeng Bai, Hailong Cao, Tiejun Zhao (2018). Improving Vector Space Word Representations Via Kernel Canonical Correlation Analysis. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP, SCI-Q4, JCR-Q4).

Cite DOI URL

Popular Topics

Academic Deep Learning dialogues generation graph neural networks Hugo machine translation pre-training semantics sentiment analysis summarization

Contact