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 task. 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.
Artificial Intelligence and Robotics
Data Management and Analytics
ICLR 2017: 5th International Conference on Learning Representations
City or Country
WANG, Shuohang and Jing JIANG.
Machine comprehension using match-LSTM and answer pointer. (2017). ICLR 2017: 5th International Conference on Learning Representations. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3654
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.