Github Links
- Improving Unsupervised Constituency Parsing via Maximizing Semantic Information. In ICLR 2025 spotlight poster
- Constituents are Frequent Word Sequences among Sentences with Equivalent Predicate-Argument Structures: Unsupervised Constituency Parsing by Span Matching. Findings of the Association for Computational Linguistics: ACL 2024
- Language Model Based Unsupervised Dependency Parsing with Conditional Mutual Information and Grammatical Constraints. In proceedings of the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
- Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models. In Proceedings of 60th Annual Meeting of the Association for Computational Linguistics