Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Machine Comprehension Using Match-LSTM and Answer Pointer
Shuohang Wang, Jing Jiang
Nov 04, 2016 (modified: Mar 13, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans through crowdsourcing. SQuAD provides a challenging testbed for evaluating machine comprehension algorithms, partly because compared with previous datasets, in SQuAD the answers do not come from a small set of candidate answers and they have variable lengths. We propose an end-to-end neural architecture for the task. The architecture is based on match-LSTM, a model we proposed previously for textual entailment, and Pointer Net, a sequence-to-sequence model proposed by Vinyals et al. (2015) to constrain the output tokens to be from the input sequences. We propose two ways of using Pointer Net for our tasks. Our experiments show that both of our two models substantially outperform the best results obtained by Rajpurkar et al. (2016) using logistic regression and manually crafted features. Besides, our boundary model also achieves the best performance on the MSMARCO dataset (Nguyen et al. 2016).
TL;DR:Using Match-LSTM and Answer Pointer to select a variable length answer from a paragraph
Keywords:Natural language processing, Deep learning
Enter your feedback below and we'll get back to you as soon as possible.