Abstract
This research studies graph-based approaches for Answer Sentence Selection (AS2), an essential component for retrieval-based Question Answering (QA) systems. During offline learning, our model constructs a small-scale relevant training graph per question in an unsupervised manner, and integrates with Graph Neural Networks. Graph nodes are question sentence to answer sentence pairs. We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs, and use thresholding on relevance scores for creating graph edges. Online inference is then performed to solve the AS2 task on unseen queries. Experiments on two well-known academic benchmarks and a real-world dataset show that our approach consistently outperforms SOTA QA baseline models.- Anthology ID:
- 2023.eacl-main.68
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 968–979
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.68
- DOI:
- 10.18653/v1/2023.eacl-main.68
- Cite (ACL):
- Roshni Iyer, Thuy Vu, Alessandro Moschitti, and Yizhou Sun. 2023. Question-Answer Sentence Graph for Joint Modeling Answer Selection. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 968–979, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Question-Answer Sentence Graph for Joint Modeling Answer Selection (Iyer et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2023.eacl-main.68.pdf