Dependent Gated Reading for Cloze-Style Question Answering

Reza Ghaeini, Xiaoli Fern, Hamed Shahbazi, Prasad Tadepalli


Abstract
We present a novel deep learning architecture to address the cloze-style question answering task. Existing approaches employ reading mechanisms that do not fully exploit the interdependency between the document and the query. In this paper, we propose a novel dependent gated reading bidirectional GRU network (DGR) to efficiently model the relationship between the document and the query during encoding and decision making. Our evaluation shows that DGR obtains highly competitive performance on well-known machine comprehension benchmarks such as the Children’s Book Test (CBT-NE and CBT-CN) and Who DiD What (WDW, Strict and Relaxed). Finally, we extensively analyze and validate our model by ablation and attention studies.
Anthology ID:
C18-1282
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3330–3345
Language:
URL:
https://aclanthology.org/C18-1282
DOI:
Bibkey:
Cite (ACL):
Reza Ghaeini, Xiaoli Fern, Hamed Shahbazi, and Prasad Tadepalli. 2018. Dependent Gated Reading for Cloze-Style Question Answering. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3330–3345, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Dependent Gated Reading for Cloze-Style Question Answering (Ghaeini et al., COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/C18-1282.pdf
Data
CBT