Xinya Du
- Assistant Professor of Computer Science
- Human Language Technology Research Institute
- University of Texas at Dallas
- Email: xinya.du AT utdallas.edu
I am Xinya Du (pronounced as shinn-ya do), a tenure-track assistant professor in the Department of Computer Science at the University of Texas at Dallas. My research focuses on in the area of Natural Language Processing (NLP) and Machine Learning. I was a Postdoctoral Research Associate at the University of Illinois at Urbana-Champaign. Before, I earned a CS Ph.D. degree from Cornell University; and graduated with a bachelor's degree in CSE from Shanghai Jiao Tong University.
My work are published in leading NLP conferences, and has been covered by major media like New Scientist [link] and included in the list of Most Influential ACL Papers (15 each year). I was named a Spotlight Rising Star in Data Science (NLP) by the University of Chicago in 2020.
New: As a faculty member of our NLP group at UTD (US top 20 in the NLP area based on CSRankings), I am looking for self-motivated PhD/Master/Intern students to work with me on core NLP and relevant research. PhD students are provided with funding support.
🌟Prospective Students: Please drop me an email including your CV/Resume, transcript and samples of your work if interested (More details Here).
Publications | Teaching & Service | Curriculum Vitae | Misc.
Recent
- Feb 2023 Joining as a panelist on "ChatGPT: Fact vs Fiction", hosted by UTD and The Dallas Morning News.
- Jan 2023 Serving as an Area Chair (IE) for ACL 2023.
- July 2022 Attending NAACL 2022 in Seattle, WA.
- May 2022 Attending ACL 2022 Virtually.
- ...
Research Interests (Publications)
I enjoy exploring/building things that are novel and impactful (in research and life). My research is motivated by building intelligent and efficient systems for core NLP problems (e.g., turning a large amount of unstructured information into a concise and structured format). Specifically, my current includes (but not limited to) developing methods encoding knowledge (contextual and external) and reasoning capabilities for question asking / generation & answering, and information extraction, as well as the interplay between them.
- Document Understanding in the Dynamic World: Extracting informative information from long documents (streams) is a challenging in information extraction, requiring a global understanding of each document. How do we represent contextual information such as "memory" and "time"? How do we build efficient systems that can detect the incoherent predictions, as well as improve their consistency.
- Reasoning Capability and Knowledge: How do we leverage contextual and external knowledge into end-to-end models, reasoning for better factual and faithful behaviors? How can we exploit and understand the reasoning capabilities of large pre-trained models?
- Question Answering: How do we build efficient (data- and computing-) models that can answer "complex and compositional" questions, and questions with non-definite answer formats in the real world? How can IE benefit question answering and how can question answering benefit IE.
- NLP and Vision / Robotics / Science : How do we design NLP techniques for interdisciplinary research, and vice versa.