Hi, I am an incoming PhD student at Virginia Tech this Fall where I will be advised by Tu Vu.
Previously, I received my Master at the Language Science and Technology Department (LST) of Saarland University, where I worked with Dietriech Klakow and Vera Demberg. Prior to that, I contributed to the development of an NLP system for historical archives with Richard Tzong-Han Tsai at Intelligent Information Service Research Lab (IISR) and Liu Yuan-ju at Academia Sinica, Taiwan.
My primary research interests broadly revolve around efficient NLP which span a wide range of captivating topics including:
- Efficient transfer learning: In-Context Prompt Editing, Open Prompt Alignment, Sample Size Determination, LED.
- NLP for low-resource languages: CaT.
These days, I’m excited about delving into the behavior of LMs — understanding how they learn and process information at different levels. Pertinent sub-questions arise, such as understanding the specific information transmitted through within-tuning phases and cross-tuning phases. Furthermore, exploring how LMs store information in their knowledge reservoirs and how they can selectively purge or forget knowledge from this reservoir.
Email: pinjie(at)vt.edu
I am actively seeking a internship/student research for Winter 2024. I invite you to review my CV for further details. CV.
🔥 News
- 2024.03: I will spend time in Taipei in March and April. Feel free to reach out if you’re in the area and would like to meet up!
- 2024.02: I successfully presented my Master thesis Exploring Task Selection for Intermediate-Task Transfer Learning.
- 2024.02: 1 paper Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin acceted at LREC-COLING 2024.
2024.01: 1 paper accepted at EACL 2023.
- 2023.12: 🎉😊 Our paper In-Context Prompt Editing For Conditional Audio Generation has been accepted at ICASSP 2024.
- 2023.12: The paper On the Open Prompt Challenge in Conditional Audio Generation has been accepted at ICASSP 2024.
- 2023.09: I have been selected for the 2023B cohort of Google’s CS Research Mentorship Program (CSRMP).
- 2023.05: 🎉🥰 Our new paper Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin has been accepted at Interspeech 2023.
2023.05: 🎉🎉 Our new paper has been accepted at ACL 2023 findings.
- 2022.10: 🎉🎉 Our new paper Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization will be presented at the workshop on Automatic Summarization for Creative Writing at COLING 2022. Our system ranks 1st in the Script-base track.
2022.04: I will present our software project for short story recommendations (with Niyati Bafna) at Saarland university.
2020.10: I start my journey at Saarland university.
- 2019.12: Our paper will be presented at conference DADH 2019.
- 2019.08: I will give a talk about Climate Event system based on Historical Meteorological Records at National Central University.
2019.08: I gave a tutorial for Hello, Sequence Labeling in the Summer Program at National Central University.
- 2018.12: Our paper will be presented at conference DADH 2018.
- 2018.07: I gave a invited talk about Python programming on Digital Humanities Workshop at National Taiwan University.
📝 Publications
* indicates equal contributions
Exploring Task Selection for Intermediate-Task Transfer Learning
Pin-Jie Lin
Master’s thesis
[Paper] [Slide]
Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin
Pin-Jie Lin, Merel Scholman, Muhammed Saeed, Vera Demberg
LREC-COLING 2024
Projecting Annotations for Discourse Relations: Connective Identification for Low Resource Languages
Peter Bourgonje, Pin-Jie Lin
To Appear at Workshop on Computational Approaches to Discourse at EACL 2024
In-Context Prompt Editing For Conditional Audio Generation
Ernie Chang*, Pin-Jie Lin*, Yang Li, Sidd Srinivasan, Gael Le Lan, David Kant, Yangyang Shi, Forrest Iandola, Vikas Chandra
ICASSP 2024
On the Open Prompt Challenge in Conditional Audio Generation
Ernie Chang, Sidd Srinivasan, Mahi Luthra, Pin-Jie Lin, Varun K. Nagaraja, Forrest Iandola, Zechun Liu, Zhaoheng Ni, Changsheng Zhao, Yangyang Shi, Vikas Chandra
ICASSP 2024
Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin
Pin-Jie Lin*, Muhammed Saeed*, Ernie Chang*, Merel Scholman
Interspeech 2023
[Paper]
Revisiting Sample Size Determination in Natural Language Understanding
Ernie Chang*, Muhammad Hassan Rashid*, Pin-Jie Lin*, Changsheng Zhao, Vera Demberg, Yangyang Shi and Vikas Chandra
ACL 2023 Findings
[Paper]
Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization
Dongqi Pu*, Xudong Hong*, Pin-Jie Lin*, Ernie Chang, Vera Demberg
COLING 2022
[Paper]
Event Extraction: Convolutional Neural Networks for Extracting Medieval Chinese Monk’s Travels
Pin-Jie Lin, Bing-Lin Tsai
International Conference of Digital Archives and Digital Humanitie 2019
Name Recognition of Medieval Chinese Monk Names
Severina Balabanova, Pin-Jie Lin, Ya-Lin Chen, Wan-Chun Chiu
International Conference of Digital Archives and Digital Humanities 2018