Abstract
Given a question and a set of answer candidates, answer triggering determines whether the candidate set contains any correct answers. If yes, it then outputs a correct one. In contrast to existing pipeline methods which first consider individual candidate answers separately and then make a prediction based on a threshold, we propose an end-to-end deep neural network framework, which is trained by a novel group-level objective function that directly optimizes the answer triggering performance. Our objective function penalizes three potential types of error and allows training the framework in an end-to-end manner. Experimental results on the WikiQA benchmark show that our framework outperforms the state of the arts by a 6.6% absolute gain under F1 measure.- Anthology ID:
- D17-1131
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1276–1282
- Language:
- URL:
- https://aclanthology.org/D17-1131
- DOI:
- 10.18653/v1/D17-1131
- Cite (ACL):
- Jie Zhao, Yu Su, Ziyu Guan, and Huan Sun. 2017. An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1276–1282, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective (Zhao et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/D17-1131.pdf