Question Answering

This project focuses on developing advanced NLP techniques to extract accurate answers from unstructured text. It tackles the complexities of interpreting diverse question types, understanding context, and retrieving relevant information from large volumes of unstructured data. The research aims to improve the accuracy, efficiency, and adaptability of question answering systems across multiple domains and languages.

Director

• Jinho Choi - Assistant Professor at Emory University

Funding

• IPSoft Inc. (09/2014 ~ 05/2015)

Distributions

• SelQA: Selection-based Question Answering
• QA-It: Non-referential It for Question Answering

Publications

1. Analysis of Wikipedia-based Corpora for Question Answering. Jurczyk, T.; Deshmane, A.; and Choi, J. D. arXiv, 1801.02073, 2018.
2. SelQA: A New Benchmark for Selection-based Question Answering. Jurczyk, T.; Zhai, M.; and Choi, J. D. Proceedings of the International Conference on Tools with Artificial Intelligence (ICTAI), 2016.
3. QA-It: Classifying Non-Referential It for Question Answer Pairs. Lee, T.; Alex, L.; and Choi, J. D. Proceedings of the Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL:SRW), 2016.
4. Multi-Field Structural Decomposition for Question Answering. Jurczyk, T.; and Choi, J. D. arXiv, 1604.00938, 2016.
5. Semantics-based Graph Approach to Complex Question-Answering. Jurczyk, T.; and Choi, J. D. Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop (NAACL:SRW), 2015.
6. Real-Time Community Question Answering: Exploring Content Recommendation and User Notification Strategies. Liu, Q.; Jurczyk, T.; Choi, J. D.; and Agichtein, E. Proceedings of the Conference on Intelligent User Interfaces (iUI), 2015.