Sequence Tagging & Structure Parsing

This project focuses on two main areas: sequence tagging to enhance accuracy in tasks such as Part-of-Speech (POS) Tagging and Named Entity Recognition (NER), which are crucial for understanding the grammatical structure and identifying key elements in text, and structure parsing to improve models for Constituency Parsing, Dependency Parsing, and Abstract Meaning Representation (AMR) Parsing to better capture the hierarchical and semantic structures of language.  By pushing the boundaries in these areas, the project seeks to improve machines' ability to understand and process human language at both syntactic and semantic levels.

Director

• Jinho Choi - Associate Professor at Emory University

Related Projects

• Emory-Yonsei Collaboration (01/2020 ~ 08/2021)
• Alexa Prize Socialbot Grand Challenge 4 (09/2020 ~ 05/2021)
• Alexa Prize Socialbot Grand Challenge 3 (09/2019 ~ 05/2020)
• Yahoo Labs (09/2014 - 05/2015)

Publications

1. Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing. He, H. and Choi, J. D. Transactions of the Association for Computational Linguistics (TACL), 2023.
   
2. The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders. He, H.; and Choi, J. D. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
3. Levi Graph AMR Parser using Heterogeneous Attention. He, H.; and Choi, J. D. Proceedings of the International Conference on Parsing Technologies (IWPT), 2021.
4. Adaptation of Multilingual Transformer Encoder for Robust Enhanced Universal Dependency Parsing. He, H.; and Choi, J. D. Proceedings of the International Conference on Parsing Technologies: Shared Task on Enhanced Universal Dependencies (IWPT:ST), 2020.
5. Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT. He, H.; and Choi, J. D. Proceedings of the International Florida Artificial Intelligence Research Society Conference (FLAIRS), 2020.
6. Dynamic Feature Induction: The Last Gist to the State-of-the-Art. Choi, J. D. Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2016.
7. It Depends: Dependency Parser Comparison Using A Web-based Evaluation Tool. Choi, J. D.; Stent, A.; and Tetreault, J. Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2015.