Dependent Gated Reading for Cloze-Style Question Answering
arXiv:1805.10528
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 \emph{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.
arXiv commentAccepted as a long paper at COLING 2018, 16 pages, 12 figures
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- Teaching Machines to Read and Comprehend
- The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
- Consensus Attention-based Neural Networks for Chinese Reading Comprehension
- Who did What: A Large-Scale Person-Centered Cloze Dataset