RikiNet: Reading Wikipedia Pages for Natural Question Answering
Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Nan Duan
Abstract
Reading long documents to answer open-domain questions remains challenging in natural language understanding. In this paper, we introduce a new model, called RikiNet, which reads Wikipedia pages for natural question answering. RikiNet contains a dynamic paragraph dual-attention reader and a multi-level cascaded answer predictor. The reader dynamically represents the document and question by utilizing a set of complementary attention mechanisms. The representations are then fed into the predictor to obtain the span of the short answer, the paragraph of the long answer, and the answer type in a cascaded manner. On the Natural Questions (NQ) dataset, a single RikiNet achieves 74.3 F1 and 57.9 F1 on long-answer and short-answer tasks. To our best knowledge, it is the first single model that outperforms the single human performance. Furthermore, an ensemble RikiNet obtains 76.1 F1 and 61.3 F1 on long-answer and short-answer tasks, achieving the best performance on the official NQ leaderboard.- Anthology ID:
- 2020.acl-main.604
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6762–6771
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.604
- DOI:
- 10.18653/v1/2020.acl-main.604
- Cite (ACL):
- Dayiheng Liu, Yeyun Gong, Jie Fu, Yu Yan, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, and Nan Duan. 2020. RikiNet: Reading Wikipedia Pages for Natural Question Answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6762–6771, Online. Association for Computational Linguistics.
- Cite (Informal):
- RikiNet: Reading Wikipedia Pages for Natural Question Answering (Liu et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/landing_page/2020.acl-main.604.pdf
- Data
- Natural Questions, SQuAD