Dependent Gated Reading for Cloze-Style Question Answering
This addresses a specific bottleneck in machine comprehension for researchers, though it appears incremental as it builds on existing reading mechanisms.
The paper tackled the cloze-style question answering task by proposing a dependent gated reading bidirectional GRU network (DGR) to model document-query interdependencies, achieving competitive performance on benchmarks like Children's Book Test and Who DiD What.
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.