Main picture

/ɥín mʷòː ʈʂʰə́n/

Bloomberg LP

Senior Scientist

Email: [email protected]

Bio

I am a Senior Scientist at Bloomberg. I obtained my PhD from Johns Hopkins University, where I was advised by Prof. Benjamin Van Durme. 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. I was awarded outstanding paper for Learning to Retrieve Iteratively for In-Context Learning at EMNLP 2024 and Iterative Document-level Information Extraction via Imitation Learning at EACL 2023.

Preprints

,
Streaming Sequence Transduction through Dynamic Compression
In arXiv:2402.01172, 2024.

Publications

,
Learning to Retrieve Iteratively for In-Context Learning
In Empirical Methods in Natural Language Processing (EMNLP), 2024.
Outstanding Paper Award
,
FaithScore: Evaluating Hallucinations in Large Vision-Language Models
In Empirical Methods in Natural Language Processing (EMNLP), findings, 2024.
,
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
In Association for Computational Linguistics (ACL), findings, 2024.
,
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
In International Conference on Machine Learning (ICML), 2024.

Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles
In North American Chapter of the Association for Computational Linguistics (NACL), 2024.
,
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.