Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems

Wang Ling, Dani Yogatama, Chris Dyer, Phil Blunsom


Abstract
Solving algebraic word problems requires executing a series of arithmetic operations—a program—to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs.
Anthology ID:
P17-1015
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
158–167
Language:
URL:
https://aclanthology.org/P17-1015
DOI:
10.18653/v1/P17-1015
Bibkey:
Cite (ACL):
Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. 2017. Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 158–167, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems (Ling et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1015.pdf
Video:
 https://aclanthology.org/P17-1015.mp4