Biography

Hi! Nice to meet you! I am Chia-Hsuan (Michael) Lee (李佳軒). I am a fourth-year PhD student at University of Washington, where I am advised by Prof. Mari Ostendorf in the Natural Language Processing Group. I also work closely with Prof. Noah A. Smith.

My research interests are deep learning/machine learning and their applications in natural language processing. My recent research interests are

• Conversational AI (IC-DST, SGP-DST)
• text-to-SQL parsing (KaggleDBQA, IC-DST)
• multilingual NLP (DOCmT5, CLQA)

I was also fortunate to be advised by Matthew Richardson and Alex Polozov at Microsoft Research, Melvin Johnson at Google Research, Ankur Bapna and Yu Zhang at Google Brain Research.

I served on organzing comittees of Multilingual Information Access Workshop and program committees of Structured and Unstructured Knowledge Integration Workshop. I review for EMNLP, ACL, NAACL, COLING and ARR.

I have a Master’s degree in computer science from National Taiwan University working with Prof. Lin-Shan Lee, Prof. Hung-Yi Lee and Prof. Yun-Nung Chen on spoken question answering (Spoken-SQuAD, ODSQA, Adversarial Learning SQA).

News

• 10/2022: Our paper on in-context learning for dialogue “IC-DST” is accepted to EMNLP2022 Findings! “Twitter”
• 06/2022: Started the internship with Ankur Bapna and Yu Zhang at Google Brain Research, New York.
• 04/2022: Our paper “DOCmT5” is accepted to NAACL2022 Findings! “Twitter”
• 03/2022: Our new preprint In-Context Learning for Few-Shot Dialogue State Tracking is out!
• 02/2022: Our workshop on Multilingual Information Access (MIA) will be held at NAACL2022 in Seattle! Call for Paper and Shared Task are out!
• 12/2021: Our new preprint on “Document-level Multillingual Pretraining” is out!
• 08/2021: Our paper “Dialogue State Tracking with a Language Model using Schema-Driven Prompting” is accepted to EMNLP2021 main conference.
• 05/2021: Will be an AI Research intern at Translation Research Team, Google this summer with Melvin Johnson.
• 05/2021: Our paper “KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers” is accpted to ACL2021 main conference. Data page and download link available!