Main picture

/ɥín mʷòː ʈʂʰə́n/

Johns Hopkins University

Ph.D. student

Email: [email protected]

Bio

I am a final year Ph.D. candidate advised by Prof. Benjamin Van Durme at Johns Hopkins University. My research interests are structured prediction (e.g. semantic parsing, code generation, information extraction) and sequence modeling (e.g. machine translation, streaming sequence transduction).

Recently, I have been working on large language models (LLMs) projects including using reinforcement learning (RL) to improve model steerability and robustness, retrieval augmented generation (RAG) for long-form question answering, and model fine-tuning with preference and demonstration data.

On the job market: I am currently on the job market looking for industry positions. Don’t hesitate to email me if there is a potential fit.

Preprints

,
Streaming Sequence Transduction through Dynamic Compression
In arXiv:2402.01172, 2024.
,
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
In arXiv:2401.13136, 2024.
,
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
In arXiv:2401.08417, 2024.

Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles
In arXiv:2311.02310, 2023.
,
FaithScore: Evaluating Hallucinations in Large Vision-Language Models
In arXiv:2311.01477, 2023.

Publications

,
MultiMUC: Multilingual Template Filling on MUC-4
In European Chapter of the Association for Computational Linguistics (EACL), 2024.
,
A Unified View of Evaluation Metrics for Structured Prediction
In Empirical Methods in Natural Language Processing (EMNLP), 2023.
,
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
In Empirical Methods in Natural Language Processing (EMNLP), 2023.
,
On Event Individuation for Document-Level Information Extraction
In Empirical Methods in Natural Language Processing (EMNLP), findings, 2023.
,
When Do Decompositions Help for Machine Reading?
In Empirical Methods in Natural Language Processing (EMNLP), 2023.
,
Iterative Document-level Information Extraction via Imitation Learning
In European Chapter of the Association for Computational Linguistics (EACL), 2023.
Outstanding Paper Award
,
Differentiable Tree Operations Promote Compositional Generalization
In International Conference on Machine Learning (ICML), 2023.
,
An Empirical Study on Finding Spans
In Empirical Methods in Natural Language Processing (EMNLP), 2022.
,
Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
In Empirical Methods in Natural Language Processing (EMNLP), 2021.
,
LOME: Large Ontology Multilingual Extraction
In Association for Computational Linguistics (ACL), System Demo, 2021.
,
Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems
In DEEP-DIAL at AAAI, 2021.
,
Hierarchical Entity Typing via Multi-level Learning to Rank
In Association for Computational Linguistics (ACL), 2020.
,
Joint Modeling of Arguments for Event Understanding
In Computational Approaches to Discourse (CODI) at EMNLP, 2020.
,
Reading the Manual: Event Extraction as Definition Comprehension
In Structured Prediction for NLP (SPNLP) at EMNLP, 2020.