Jiangjie Chen

Jiangjie Chen

Ph.D. Candidate

Fudan University

Biography

Jiangjie Chen (ι™ˆζ±Ÿζ·) is a fourth-year Ph.D. candidate at Fudan University (FDU) in School of Computer Science, Shanghai, China, where he is advised by Prof. Yanghua Xiao at Knowledge Works Lab. He is also currently a research intern at ByteDance AI Lab and UCSB.

He is devoted to reasoning over natural language and making machines being right for the right reasons. His main interested research topics include (but not limited to):

  1. Machine Reasoning, especially on endowing various kinds of human-like reasoning abilities to language models, including analogical reasoning, counterfactual reasoning, decision-making, planning, etc.;
  2. Text Generation, especially on the building of factual, faithful, controllable and knowledge-guided text generation techniques;
  3. The intersect of machine reasoning and text generation, i.e., achieving machine reasoning with the vehicle of natural language, especially with free-text rationales generated by language models.

His previous research experiences also include Knowledge Acquisition.

( Download my resumé. Could be outdated. 😢)

Interests
  • Language Reasoning
  • Language Generation
  • Knowledge Acquisition and Application
  • Mountaineering πŸ§—β€β™‚οΈ
  • Tennis 🎾 (3.0)
Education
  • Ph.D. in CS, 2019 - 2024 (estimated)

    Fudan University

  • B.S. in CS (with honor), 2014 - 2019

    Fudan University

News

  • [9/18/2022] We officially release a new version of the E-KAR dataset (v1.0 -> v1.1), with a substantially improved English dataset! Over 600 problems and 1,000 explanation texts are manually adjusted, and we are as strict as we can! See more information at the E-KAR project page. Have fun!

  • [7/27/2022] Talk@ε°†ι—¨εˆ›ζŠ• titled “Right for the Right Reasons: Explainable Reasoning on Analogical Recognition and Fact Verification” (in Chinese).

  • [7/13/2022] ACT for NAT will be presented at NAACL-HLT 2022.

  • [5/27/2022] E-KAR will be presented at the Commonsense Representation and Reasoning (CSRR) workshop at ACL 2022, discussions welcomed!

  • [5/25/2022] E-KAR will be presented at ACL 2022 (virtually) in a poster session, welcome to check it out!

  • [4/8/2022] Our paper (ACT) got accepted at NAACL-HLT 2022!

  • [3/26/2022] The leaderboard of E-KAR has been released at EvalAI! Welcome to participate!

  • [3/19/2022] Our work LOREN received the attention of WikiResearch Team 🧐, here’s the tweet.

  • [2/25/2022 ~ 2/28/2022] Giving oral & poster presentations about LOREN and EDUCAT at AAAI 2022 virtual conference.

  • [2/24/2022] Our paper (E-KAR) got accepted at ACL 2022 (Findings)!

Experience

 
 
 
 
 
University of California, Santa Barbra
Research Intern
University of California, Santa Barbra
Sep 2021 – Present Remote
Natural language reasoning, hosted by Prof. Lei Li.
 
 
 
 
 
ByteDance AI Lab
Research Intern
ByteDance AI Lab
Nov 2019 – Present Shanghai
Knowledge-guided text generation and natural language reasoning, working with Dr. Changzhi Sun and previously with Prof. Hao Zhou and Prof. Lei Li.
 
 
 
 
 
Knowledge Works Lab (KW, ηŸ₯θ―†ε·₯场) at Fudan University
Student Researcher
Knowledge Works Lab (KW, ηŸ₯θ―†ε·₯场) at Fudan University
Apr 2017 – Present Shanghai
Knowledge graph, text generation and reasoning, advised by Prof. Yanghua Xiao.

Recent Publications

Quickly discover relevant content by filtering publications.
(2022). Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints. In The 2022 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT 2022).

PDF Cite Code Slides Video

(2022). E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning. In The 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022) - Findings.

PDF Cite Project Poster Slides Video

(2022). FalCon: A Faithful Contrastive Framework for Response Generation in TableQA Systems. In The 27th International Conference on Database Systems for Advanced Applications (DASFAA 2022).

PDF Cite Code

(2022). LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification. In The 36th AAAI Conference on Artificial Intelligence (AAAI 2022) (oral).

PDF Cite Code Poster Slides Video Demo Blog

(2022). Unsupervised Editing for Counterfactual Stories. In The 36th AAAI Conference on Artificial Intelligence (AAAI 2022) (oral).

PDF Cite Code Poster Slides Video

Visitors