Basic Information
Last Updated: 03/25/2024
I am in search of a Ph.D. position in 2024, preferably in America.
I am the ideal match for your needs, if you're seeking students with a robust foundation in:
NLP (LLMs), human cognition, and education (including computer science, STEM).
I am passionate about building anthropomorphic robots to enhance human life, especially for the underprivileged. Specifically, I endeavor to devise intelligent agents that emulate human understanding and reasoning of world events. In contrast to human learning, which assimilates and accommodates information into brain schemas (Piaget, J., 1952), a significant challenge with current Language Models (LMs), including the SOTA GPT-4, is their inability to automatically acquire and anchor structured knowledge in the network. This deficiency leads to unreliable reasoning and hallucinations. To alleviate it, my research directs LMs to construct and reason with structured and symbolic representations. These efforts include event extraction, schema induction, entity-state tracking, and Natural to Symbolic reasoning.
To know more about my experience, please check my CV, and SOP.
To know more about my research, please check my research projects. [slides] [video recording]
If you are interested in my work, feel free to email me.
Research Interests:
- Reasoning in Natural/Symbolic Language
- Interdisciplinary in NLP, CV and Robotics
Expertise:
- Learning Science and Cognitive Science (6 years of experience, B.S., M.Ed)
- Human Learning and Knowledge Storage
- Learning Task Design
- Natural Language Processing (3 years of experience, MSE)
- Event Extraction
- Event Reasoning in Natural and Symbolic Language
e.g. Schema Generation, Event and Entity Pre- and Post-condition Generation
Publications
Human-in-the-Loop Schema Induction. Tianyi Zhang*, Isaac Tham*, Zhaoyi Hou*, Jiaxuan Ren, Liyang Zhou, Hainiu Xu, Li Zhang, Lara J. Martin, Rotem Dror, Sha Li, Heng Ji, Martha Palmer, Susan Brown, Reece Suchocki, Chris Callison-Burch. ACL Demo 2023
Question-Answer Data Augmentation for Argument Role Labeling. Tianyi Zhang, Elior Sulem, Dan Roth. 2023, In submission
PROC2PDDL: Towards Open-Domain Symbolic Planning. Tianyi Zhang*, Li Zhang*, Zhaoyi Hou, Ziyu Wang, Yuling Gu, Peter Clark, Chris Callison-Burch, Niket Tandon. 2023, In submission
Education
- MSE in Data Science, Jan. 2021 - Dec. 2022
University of Pennsylvania, Philadelphia, America - M.Ed in Learning Science and Technology, Sept. 2018 - Dec. 2019
University of Pennsylvania, Philadelphia, America - B.S in Educational Technology, Sept. 2014 - Jun. 2018
Beijing Normal University, Beijing, China
Research Experience
- Research Assistant: NLP Group at UPenn, May. 2022 - Jul. 2023
- Research Assistant: Cognitive Computation Group at UPenn, Mar. 2020 – Dec. 2022