Yunshi Lan (兰韵诗)
School of Data Science and Engineering, East China Normal University (ECNU)
Address: 3663 North ZhongshanRd, Putuo District, Shanghai, China
Office: Room 203, Geography Building
Email: yslan [at] dase.ecnu.edu.cn

About Me ([GitHub] [Google Scholar]

I am currently an Associate Professor at the School of Data Science & Engineering, East China Normal University (ECNU). Before that, I was a research scientist at LARC, Singapore Management University (SMU). I obtained my Ph.D degree from School of Computing & Information System, Singapore Management University. I was trained (by my amazing supervisor Prof. Jing Jiang and secondary supervisor Prof. Feida Zhu) to be a NLP researcher. I received my Bachelor degree from the School of Mathematics and Statistics, Southwest University (SWU).

Research Interest

My recent research interest mainly includes knowledge bases, question answering, information extraction, text generation, deep learning and large language models.
I am looking for self-motivated students with strong programming skill to work with me. Please read this FAQ before emailing me!
2024年研究生名额已满,25年获得华师大数据学院保研/考研录用的同学欢迎联系我

News

         [2023]
  • 2023-12: We won the Best Innovation Award in Yangtze River Delta Fintech Innovation & Application Global Competition.
  • 2023-10: Two paper about Question Answering and Chain-of-Thought were accepted by EMNLP 2023.
  • 2023-09: One paper about FL was accepted by NeurIPS 2023.
  • 2023-08: One paper about Chinese Grammar Error Correction dataset was accepted by ACM CIKM 2023.
  • 2023-07: One paper about Knowledge Base Visual Question Answering was accepted by ACM MM 2023.
  • 2023-06: Rank First in the evaluation of NLPCC2023 Shared Task 8: Chinese Spelling Check.
  • 2023-05: Three papers about Question Answering, Math Word Problem Solving were accepted by ACL 2023.
  • 2023-04: One paper about FL was accepted by CVPR 2023.

Research Highlights ([Full List])

Question Answering

We have developed question answering systems under different scenarios. For Machine Reading Comprehension (MRC), we proposed different methods to improve the accuracy of answering questions over passages [AAAI'20; ACL'23]. For Knowledge Graph Question Answering (KGQA), we investegated and improved different modules in the QA framework, which achieve SOTA results in a variety of scenarios (e.g., simple questions [IJCAI'19], complex questions [WSDM'20; ACL'20; ACL'23], conversational questions [ACL'21]). For Question Answering with Databases, we explored to generate complex questions in a low-resource condition [EMNLP'23] and align Large Language Models (LLMs) to a domain-specific database [ArXiv]. For Multi-modal Question Answering, we discussed the applications of LLMs and its safety issue [MM'23; IJCAI'24;ECCV'24].
There are surveys [TKDE'22] you can start with. We have demonstration pages [Demonstration Page] that you can try on!

Educational NLP

We have worked on the educational NLP tasks, such as Math Word Problem (MWP) solving [AAAI demo'22; ACL'23; EMNLP Finding'23], Chinese Spelling Check (CSC) [NLPCC'23], Grammatical Error Correction (GEC) [CIKM'23], Text Simplification [COLING'24].
There are surveys [ArXiv] you can start with.

Selected Papers

(* indicates equal contribution, # indicates corresponding author)
  • FinQA: A Training-free Dynamic Knowledge Graph Question Answering System in Finance with LLM-based Revision
    Wenbiao Tao, Hanlun Zhu*, Keren Tan, Jiani Wang, Yuanyuan Liang, Huihui Jiang, Pengcheng Yuan, Yunshi Lan#
    ECML-PKDD, 2024


Grants

  • Jan. 2023 - Dec. 2025: Knowledge Base Question Answering System in Interactive Environments
    National Science Foundation of China, PI
  • Jan. 2024 - Dec. 2027: Intelligent Low Carbon Oriented Theories and Critical Techniques for Perception and inference of Cross-Border Electric Power Trading Big Data
    National Science Foundation of China, ECNU PI
  • Oct. 2022 - Sep. 2024: Knowledge Base Construction and Question Answering for an Education Intelligent Platform
    Shanghai Pujiang Talent Program, PI
  • July. 2022 - Dec. 2023: Online Education Toolkit and Platform Development for International Chinese Education
    East China Normal University, PI (Completed)
  • Aug. 2023 - Dec. 2023: Financial KBQA collaborating with Large Language Models
    Joint Reseach Program with Guotai Junan Securities, PI (Completed)
  • Sep. 2023 - Sep. 2024: Question Answering System in PolarDB Community
    Joint Reseach Program with Alibaba Cloud, ECNU Co-PI
  • Jan. 2024 - Dec. 2025: Researches on International Education of Chinese and Computer Science with LLMs
    East China Normal University, PI
  • Jan. 2024 - Dec. 2028: Researches on Knowledge Mining based on Scientific Data and Literature
    National Science Foundation of China, ECNU PI

Teaching


Professional Service

  • I have served as a session chair in EMNLP 2023
  • I regularly serve as the reviewer of ACL, EMNLP, AAAI, IJCAI

Invited Talk

  • Invited Talk on Applications of Large Language Models on Finance Domain.
    ECNU (2023.12)
  • Invited Talk on Knowledge-based Question Answering with Large Language Models. [Slides]
    NUST, NLP Group (2023.11)
    SCU, NLP Group (2023.12)

Mentoring Experience

Master students

  • Zeyu Sheng (CCL 2023) (ECNU -> ByteDance, Shanghai); Xuyao Hu (ECNU -> Xiecheng, Shanghai); Yuze Huang (ECNU -> Xiecheng, Shanghai); Yuxuan Huang (ECNU -> Shanghai Stock Exchange, Shanghai)
  • Keren Tan (中文信息学报; COLING 2024; ECML-PKDD 2024; Shanghai excellent graduate student 2024) (ECNU -> Guotai Junan Securities, Shanghai); Jiani Wang (CIKM 2023; ECML-PKDD 2024) (ECNU -> Midea, Shanghai); Lei Pan(ECNU -> AISPEECH, Shanghai)

Undergraduate students

  • Qingyuan Tian (CIKM 2023; EMNLP Finding 2023) (ECNU -> PhD candidate, SJTU)