Abstract
The model submitted works as follows. When supplied a question and a passage it makes use of the BERT embedding along with the hierarchical attention model which consists of 2 parts, the co-attention and the self-attention, to locate a continuous span of the passage that is the answer to the question.- Anthology ID:
- D19-5825
- Volume:
- Proceedings of the 2nd Workshop on Machine Reading for Question Answering
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, Danqi Chen
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 191–195
- Language:
- URL:
- https://aclanthology.org/D19-5825
- DOI:
- 10.18653/v1/D19-5825
- Cite (ACL):
- Reham Osama, Nagwa El-Makky, and Marwan Torki. 2019. Question Answering Using Hierarchical Attention on Top of BERT Features. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 191–195, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Question Answering Using Hierarchical Attention on Top of BERT Features (Osama et al., 2019)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/D19-5825.pdf