Frame-Based Calculus of Solving Arithmetic Multi-Step Addition and Subtraction Word Problems

Ma, Yuanliang; Zhou, Ying; Guang, Cui; Ren, Yun; Huang, Ronghuai

doi:10.1109/etcs.2010.316

Cited by 35 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liguda and Pfeiffer Liguda and Pfeiffer (2012) propose modeling math word problems with augmented semantic networks. In addition, Addition/subtraction problems are studied most Briars and Larkin (1984); Dellarosa (1986);Bakman (2007); Yuhui et al (2010); Roy et al (2015).…”

Section: Math Word Problems Solvingmentioning

confidence: 99%

Deep Neural Solver for Math Word Problems

Wang¹,

Liu²,

Shi³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

246

201

View full text Add to dashboard Cite

This paper presents a deep neural solver to automatically solve math word problems. In contrast to previous statistical learning approaches, we directly translate math word problems to equation templates using a recurrent neural network (RNN) model, without sophisticated feature engineering. We further design a hybrid model that combines the RNN model and a similarity-based retrieval model to achieve additional performance improvement. Experiments conducted on a large dataset show that the RNN model and the hybrid model significantly outperform stateof-the-art statistical learning methods for math word problem solving.

show abstract

Section: Math Word Problems Solvingmentioning

confidence: 99%

Deep Neural Solver for Math Word Problems

Wang¹,

Liu²,

Shi³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

246

201

View full text Add to dashboard Cite

show abstract

“…Math equations are then derived from the structured representation. Addition/subtraction problems are studied most in early research (Briars and Larkin, 1984;Fletcher, 1985;Dellarosa, 1986;Bakman, 2007;Yuhui et al, 2010). Please refer to Mukherjee and Garain (2008) for a review of symbolic approaches before 2008.…”

Section: Math Word Problem Solvingmentioning

confidence: 99%

How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation

Huang¹,

Shi²,

Lin³

et al. 2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

107

View full text Add to dashboard Cite

Recently a few systems for automatically solving math word problems have reported promising results. However, the datasets used for evaluation have limitations in both scale and diversity. In this paper, we build a large-scale dataset which is more than 9 times the size of previous ones, and contains many more problem types. Problems in the dataset are semiautomatically obtained from community question-answering (CQA) web pages. A ranking SVM model is trained to automatically extract problem answers from the answer text provided by CQA users, which significantly reduces human annotation cost. Experiments conducted on the new dataset lead to interesting and surprising results.

show abstract

“…Automatic math word problem solving methods (Bobrow, 1964a,b;Charniak, 1968Charniak, , 1969Briars and Larkin, 1984;Fletcher, 1985;Dellarosa, 1986;Bakman, 2007;Yuhui et al, 2010) developed before 2008 are mostly rule-based. They accept limited well-format input sentences and map them into certain structures by pattern matching.…”

Section: Related Workmentioning

confidence: 99%

Learning Fine-Grained Expressions to Solve Math Word Problems

Huang¹,

Shi²,

Lin³

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

This paper presents a novel templatebased method to solve math word problems. This method learns the mappings between math concept phrases in math word problems and their math expressions from training data. For each equation template, we automatically construct a rich template sketch by aggregating information from various problems with the same template. Our approach is implemented in a two-stage system. It first retrieves a few relevant equation system templates and aligns numbers in math word problems to those templates for candidate equation generation. It then does a fine-grained inference to obtain the final answer. Experiment results show that our method achieves an accuracy of 28.4% on the linear Dolphin18K benchmark, which is 10% (54% relative) higher than previous stateof-the-art systems while achieving an accuracy increase of 12% (59% relative) on the TS6 benchmark subset.

show abstract

Frame-Based Calculus of Solving Arithmetic Multi-Step Addition and Subtraction Word Problems

Cited by 35 publications

References 10 publications

Deep Neural Solver for Math Word Problems

Deep Neural Solver for Math Word Problems

How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation

Learning Fine-Grained Expressions to Solve Math Word Problems

Contact Info

Product

Resources

About