Dependent Gated Reading for Cloze-Style Question Answering

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.

[1]  Ting Liu,et al.  Attention-over-Attention Neural Networks for Reading Comprehension , 2016, ACL.

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[4]  Rudolf Kadlec,et al.  Text Understanding with the Attention Sum Reader Network , 2016, ACL.

[5]  David A. McAllester,et al.  Who did What: A Large-Scale Person-Centered Cloze Dataset , 2016, EMNLP.

[6]  Wang Ling,et al.  Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation , 2015, EMNLP.

[7]  Jason Weston,et al.  The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations , 2015, ICLR.

[8]  Ting Liu,et al.  Consensus Attention-based Neural Networks for Chinese Reading Comprehension , 2016, COLING.

[9]  Wilson L. Taylor,et al.  “Cloze Procedure”: A New Tool for Measuring Readability , 1953 .

[10]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[11]  Philip Bachman,et al.  Natural Language Comprehension with the EpiReader , 2016, EMNLP.

[12]  Hong Yu,et al.  Reasoning with Memory Augmented Neural Networks for Language Comprehension , 2017, ICLR.

[13]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[14]  Ye Yuan,et al.  Words or Characters? Fine-grained Gating for Reading Comprehension , 2016, ICLR.

[15]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[16]  Philip Bachman,et al.  Iterative Alternating Neural Attention for Machine Reading , 2016, ArXiv.

[17]  Peng Li,et al.  Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering , 2016, ArXiv.

[18]  Ruslan Salakhutdinov,et al.  Gated-Attention Readers for Text Comprehension , 2016, ACL.

[19]  Zhong Zhou,et al.  Tweet2Vec: Character-Based Distributed Representations for Social Media , 2016, ACL.

[20]  Danqi Chen,et al.  A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task , 2016, ACL.

[21]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.