Journal
PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1
Volume -, Issue -, Pages 593-602Publisher
ASSOC COMPUTATIONAL LINGUISTICS-ACL
DOI: 10.18653/v1/P17-1055
Keywords
-
Funding
- National 863 Leading Technology Research Project [2015AA015409]
Ask authors/readers for more resources
Cloze-style reading comprehension is a representative problem in mining relationship between document and query. In this paper, we present a simple but novel model called attention-over-attention reader for better solving cloze-style reading comprehension task. The proposed model aims to place another attention mechanism over the document-level attention and induces attended attention for final answer predictions. One advantage of our model is that it is simpler than related works while giving excellent performance. In addition to the primary model, we also propose an N-best re-ranking strategy to double check the validity of the candidates and further improve the performance. Experimental results show that the proposed methods significantly outperform various state-of-the-art systems by a large margin in public datasets, such as CNN and Children's Book Test.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available