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年尚有一个专业硕士名额,请已获得华师大数据学院保研/考研录用的同学联系我

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])

(* indicates equal contribution, # indicates corresponding author)

Question Answering

Sync-FinQA: A Training-free Question Answering System Synchronizing with Dynamic Knowledge Graph in Finance
Wenbiao Tao, Hanlun Zhu*, Keren Tan, Jiani Wang, Yuanyuan Liang, Huihui Jiang, Pengcheng Yuan, Yunshi Lan#
Preprint, 2024
[Demonstration Page]
We develop a training-free KGQA demonstration system in Finance domain, which could support a wide range of financial inquiries based on a updating KG.
Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation
Yuanyuan Liang, Jianing Wang, Hanlun Zhu, Lei Wang, Yunshi Lan#, Weining Qian
EMNLP, 2023
[Paper] [BibTex]
We leverage chain-of-thought to guide LLMs to generate complicated questions over knowledge base.
Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
Yunshi Lan, Alex Xiang Li, Xin Liu, Yang Li, Wei Qin, Weining Qian
ACM MM, 2023
[Paper] [BibTex]
We propose a prompting method for visual question answering which can bridge the gap between questions and images.
Complex Knowledge Base Question Answering: A Survey
Yunshi Lan, Gaole He*, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao and Ji-Rong Wen
TKDE, 2022
[Paper] [中文解读] [GitHub Page] [BibTex]
If you would like to know Knowledge Base Question Answering, please start from this survey!
Modeling Transitions of Focal Entities for Conversational knowledge Base Question Answering
Yunshi Lan, Jing Jiang
ACL, 2021
[Paper] [BibTex]
We propose a method for conversational knowledge base question answering tasks with the consideration of the transition of focal entitites.
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
Gaole He, Yunshi Lan, Jing Jiang, Xin Zhao, Ji-Rong Wen
WSDM, 2021
[Paper] [GitHub Page] [BibTex]
We propose a method for multi-hop knowledge base question answering tasks with a Teacher-student framework.
Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases
Yunshi Lan, Jing Jiang
ACL, 2020
[Paper] [GitHub Page] [BibTex]
We propose a method for multi-hop knowledge base question answering tasks with iterative path search.

Educational NLP

Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends
Yunshi Lan, Xinyuan Li, Hanyue Du, Xuesong Lu, Ming Gao, Weining Qian, Aoying Zhou
Preprint, 2024 [Paper] [GitHub Page]
This is a survey of NLP in Education Domian, which reviews existing studies in the technical perspective.
MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers
Yihuai Lan, Lei Wang, Qiyuan Zhang, Yunshi Lan#, Bing Tian Dai, Yan Wang, Dongxiang Zhang, Ee-Peng Lim
AAAI, demo paper, 2022
[Paper] [中文解读] [GitHub Page] [BibTex]
We develop a deep learning-based MWP toolkit, so that you can design your own MWP models effectively. Please feel free to try it out!
Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement
Alex Xiang Li, Hanyue Du, Yike Zhao, Yunshi Lan#
NLPCC, evaluation paper, 2023
[Paper] [GitHub Page] [Leaderboard] [BibTex]
We rank first in NLPCC 2023 shared task Chinese Spelling Check. Please check out our open-source solution.
FlaCGEC: A Chinese Grammatical Error Correction Dataset with Fine-grained Linguistic Annotation
Hanyue Du, Yike Zhao, Qingyuan Tian, Jiani Wang, Lei Wang, Yunshi Lan#, Xuesong Lu
ACM CIKM, resource paper, 2023
[Paper] [BibTex] [GitHub Page]
We introduce a Chinese GEC dataset with fine-grained linguistic annotation.
An LLM-Enhanced Adversarial Editing System for Lexical Simplification
Keren Tan, Kangyang Luo, Yunshi Lan#, Zheng Yuan and Jinlong Shu
COLING, 2024
[Paper]
We propose a novel LS method without parallel corpora, which includes an innovative LLM-enhanced loss to enable the distillation of knowledge from Large Language Models (LLMs) into a small-size LS system.

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, Key Program, Co-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
  • Aug. 2023 - Dec. 2023: Financial KBQA collaborating with Large Language Models
    Joint Reseach Program with Guotai Junan Securities, PI
  • Sep. 2023 - Sep. 2024: Question Answering System in PolarDB Community
    Joint Reseach Program with Alibaba Cloud, Co-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)

Undergraduate students

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