Paper Info
Title
MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning.
Abstract
Designing an automatic solver for math word problems has been considered as a crucial step towards general AI, with the ability of natural language understanding and logical inference. The state-of-the-art performance was achieved by enumerating all the possible expressions from the quantities in the text and customizing a scoring function to identify the one with the maximum probability. However, it incurs exponential search space with the number of quantities and beam search has to be applied to trade accuracy for efficiency. In this paper, we make the first attempt of applying deep reinforcement learning to solve arithmetic word problems. The motivation is that deep Q-network has witnessed success in solving various problems with big search space and achieves promising performance in terms of both accuracy and running time. To lit the math problem scenario, we propose our MathDQN that is customized from the general deep reinforcement learning framework. Technically, we design the states, actions, reward function, together with a feed-forward neural network as the deep Q-network. Extensive experimental results validate our superiority over state-of-the-art methods. Our MathDQN yields remarkable improvement on most of datasets and boosts the average precision among all the benchmark datasets by 15%.
Year
Venue
Field
2018
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
Word problem (mathematics education),Computer science,Arithmetic,Reinforcement learning
DocType
Citations 
PageRank 
Conference
2
0.35
References 
Authors
14
6
Name
Order
Citations
PageRank
Lei Wang184.05
Dongxiang Zhang274343.89
Lianli Gao355042.85
Jingkuan Song4197077.76
Long Guo5654.17
Heng Tao Shen66020267.19