Scholar
Pin-Jie Lin
Google Scholar ID: KYeOpSoAAAAJ
PhD, Virginia Tech
Citations & Impact
Citations
56
H-index
5
i10-index
1
Publications
12
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- 1. 'Target-Aware Language Modeling via Granular Data Sampling' accepted to EMNLP 2024 Industry Track.
- 2. 'Exploring the Effectiveness and Consistency of Task Selection in Intermediate-Task Transfer Learning' accepted to ACL 2024 SRW.
- 3. 'Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin' accepted to LREC-COLING 2024.
- 4. 'Projecting Annotations for Discourse Relations' accepted to CODI @ EACL 2024.
Research Experience
- Contributed to NLP research on historical archives at Academia Sinica; selected as a Google CSRMP Fellow in 2023.
Education
- Ph.D. in Computer Science at Virginia Tech, advised by Tu Vu; M.S. in Language Science and Technology from Saarland University, where he worked with Dietrich Klakow and Vera Demberg.
Background
- Research interests: Developing efficient, modular LLMs for multilingual, multitask, and multimodal deployments through collaborative and communal machine learning. Focuses on efficient model development, parameter-efficient transfer learning, advanced reasoning, instruction tuning, and data-centric methods.
Miscellany
- Seeking a 2025 internship position.
