Weinan He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Weinan He has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Canming Huang
Dept. of Computer Science Sun Yat-sen University 510006 Guangzhou China
2 shared publications - Yongmei Liu
Dept. of Computer Science Sun Yat-sen University 510006 Guangzhou China
2 shared publications Zhanhao Xiao
Dept. of Computer Science Sun Yat-sen University 510006 Guangzhou China
1 shared publication- Zhanhao Xiao
Guangdong Polytechnic Normal University
1 shared publication
Latest Publications
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 4629-4643
Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change
Weinan He, Canming Huang, Zhanhao Xiao, Yongmei Liu. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 4629-4643
Open AccessExploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change
Weinan He, Canming Huang, Zhanhao Xiao, Yongmei Liu. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- Open Access
TRAC: A Textual Benchmark for Reasoning about Actions and Change
Reasoning about actions and change (RAC) is essential to understand and interact with the ever-changing environment. Previous AI research has shown the importance of fundamental and indispensable knowledge of actions, i.e., preconditions and effects. However, traditional methods rely on logical formalization which hinders practical applications. With recent transformer-based language models (LMs), reasoning over text is desirable and seemingly feasible, leading to the question of whether LMs can effectively and efficiently learn to solve RAC problems. We propose four essential RAC tasks as a comprehensive textual benchmark and generate problems in a way that minimizes the influence of other linguistic requirements (e.g., grounding) to focus on RAC. The resulting benchmark, TRAC, encompassing problems of various complexities, facilitates a more granular evaluation of LMs, precisely targeting the structural generalization ability much needed for RAC. Experiments with three high-performing transformers indicates that additional efforts are needed to tackle challenges raised by TRAC.
Open AccessTRAC: A Textual Benchmark for Reasoning about Actions and Change
Reasoning about actions and change (RAC) is essential to understand and interact with the ever-changing environment. Previous AI research has shown the importance of fundamental and indispensable knowledge of actions, i.e., preconditions and effects. However, traditional methods rely on logical formalization which hinders practical applications. With recent transformer-based language models (LMs), reasoning over text is desirable and seemingly feasible, leading to the question of whether LMs can effectively and efficiently learn to solve RAC problems. We propose four essential RAC tasks as a comprehensive textual benchmark and generate problems in a way that minimizes the influence of other linguistic requirements (e.g., grounding) to focus on RAC. The resulting benchmark, TRAC, encompassing problems of various complexities, facilitates a more granular evaluation of LMs, precisely targeting the structural generalization ability much needed for RAC. Experiments with three high-performing transformers indicates that additional efforts are needed to tackle challenges raised by TRAC.