Hi, I am Katherine.

I am a Ph.D. student at the research lab LISN of CNRS and Université Paris-Saclay in France , jointly advised by Prof. Thomas Lavergne and Pierre Zweigenbaum. I am also a member of KEEPHA: Knowledge-Enhanced information Extraction across languages for PHArmacovigilance, a trilateral collaboration among Japan, Germany, and France. Before that, I obtained my master’s degree in Computer Science from Saarland University and worked as a Research Assistant at the Computational Linguistics and Phonetics Department.

My doctoral research focused on leveraging the knowledge base to help extract information for drug studies. Under the scope of the KEEPHA project, I visited our collaborators, spending three months at the Social Computing Lab at NAIST in Nara, Japan and three months at DFKI in Berlin, Germany in 2023. I am on track to complete my PhD by the end of 2024.

Interests

  • Information Extraction
  • Knowledge Base
  • Low-Resource Learning

News

Publications

A Dataset for Pharmacovigilance in German, French, and Japanese: Annotating Adverse Drug Reactions across Languages
Lisa Raithel*,
Hui-Syuan Yeh*
, Shuntaro Yada, Cyril Grouin, Thomas Lavergne, Aurélie Névéol, Patrick Paroubek, Philippe Thomas, Tomohiro Nishiyama, Sebastian Möller, Eiji Aramaki, Yuji Matsumoto, Roland Roller, Pierre Zweigenbaum (*equal contribution)
Proceedings of LREC-COLING 2024. Awaiting conference proceedings.
[paper] | [code]
Ntcir-17 mednlp-sc social media adverse drug event detection: Subtask overview
Shoko Wakamiya, Lis Kanashiro Pereira, Lisa Raithel,
Hui-Syuan Yeh
, Peitao Han, Seiji Shimizu, Tomohiro Nishiyama, Gabriel Herman Bernardim Andrade, Noriki Nishida, Hiroki Teranishi, et al.
Workshop at NTCIR 2023
[paper]
KEEPHA at n2c2 2022: Track 1
Lisa Raithel*, Faith W. Mutinda*„ Gabriel H. B. Andrade*,
Hui-Syuan Yeh*
, Tomohiro Nishiyama, Mathieu Laï-King, Shuntaro Yada, Roland Roller, Cyril Grouin, Agata Savary, et al. (*euqal contribution)
n2c2 Shared Task and Workshop at AMIA Fall Symposium 2022
[paper]
Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extraction
Hui-Syuan Yeh
, Thomas Lavergne, Pierre Zweigenbaum
Proceedings of LREC 2022
[paper] | [code]
Logic-Guided Message Generation from Raw Real-Time Sensor Data
Ernie Chang, Alisa Kovtunova, Stefan Borgwardt, Vera Demberg, Kathryn Chapman,
Hui-Syuan Yeh
Proceedings of LREC 2022
[paper]
Time-Aware Ancient Chinese Text Translation and Inference
Ernie Chang*, Yow-Ting Shiue*,
Hui-Syuan Yeh
, Vera Demberg (*equal contribution)
Workshop on Computational Approaches to Historical Language Change associated with ACL 2021
[paper]
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning
Ernie Chang,
Hui-Syuan Yeh
, Vera Demberg
Proceedings of EACL 2021
[paper]
On Training Instance Selection for Few-Shot Neural Text Generation
Ernie Chang, Xiaoyu Shen,
Hui-Syuan Yeh
, Vera Demberg
Proceedings of ACL 2021, short paper
[paper]