Parsing Algebraic Word Problems into Equations

Koncel-Kedziorski, Rik; Hajishirzi, Hannaneh; Sabharwal, Ashish; Etzioni, Oren; Ang, Siena Dumas

doi:10.1162/tacl_a_00160

Cited by 169 publications

(210 citation statements)

References 20 publications

Supporting

Mentioning

197

Contrasting

Unclassified

Order By: Relevance

“…After that, Roy and Roth (2015) proposed an algorithmic approach which could handle arithmetic word problems with multiple steps and operations. Koncel-Kedziorski et al (2015) further Figure 1: The framework of our NumNet model. Our model consists of an encoding module, a reasoning module and a prediction module.…”

Section: Arithmetic Word Problem Solvingmentioning

confidence: 99%

NumNet: Machine Reading Comprehension with Numerical Reasoning

Ran¹,

Lin²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human's reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems. To address this issue, we propose a numerical MRC model named as NumNet, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage. Our system achieves an EM-score of 64.56% on the DROP dataset, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers.

show abstract

Section: Arithmetic Word Problem Solvingmentioning

confidence: 99%

NumNet: Machine Reading Comprehension with Numerical Reasoning

Ran¹,

Lin²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…In contrast, our work is concerned with general-purpose textual entailment which considers if a given sentence can be inferred from another. Our work also relates to solving arithmetic word problems (Hosseini et al, 2014;Mitra and Baral, 2016;Zhou et al, 2015;Upadhyay et al, 2016;Huang et al, 2017;Kushman et al, 2014a;Koncel-Kedziorski et al, 2015;? ;Roy, 2017;.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, our framework uses integer linear programming (ILP) to constrain the equation space. It is inspired by prior work on algebra word problems (Koncel-Kedziorski et al, 2015), with some key differences:…”

Section: Quantity Compositionmentioning

confidence: 99%

EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference

Ravichander

Naik

Rosé

et al. 2019

Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

Quantitative reasoning is a higher-order reasoning skill that any intelligent natural language understanding system can reasonably be expected to handle. We present EQUATE 1 (Evaluating Quantitative Understanding Aptitude in Textual Entailment), a new framework for quantitative reasoning in textual entailment. We benchmark the performance of 9 published NLI models on EQUATE, and find that on average, state-of-the-art methods do not achieve an absolute improvement over a majority-class baseline, suggesting that they do not implicitly learn to reason with quantities. We establish a new baseline Q-REAS that manipulates quantities symbolically. In comparison to the best performing NLI model, it achieves success on numerical reasoning tests (+24.2%), but has limited verbal reasoning capabilities (-8.1%). We hope our evaluation framework will support the development of models of quantitative reasoning in language understanding.

show abstract

“…Semi-Markov Variant: Our first variant, namely QT(S), employs the semi-Markov assumption (Sarawagi and Cohen, 2005), where N nodes are removed. Different from QT which makes the first-order Markov assumption, QT(S) assumes L Model AddSub AS CN Hosseini et al (2014) 77.70 - 64.00 -Koncel- Kedziorski et al (2015) 77.00 - Roy and Roth (2015) 78.00 47.57 Zhou et al (2015) 53.14 51.48 Mitra and Baral (2016) 86.07 - Roy and Roth (2017) 60 . Figure 2, the token "There" in t may not belong to any spans.…”

Section: Model Variantsmentioning

confidence: 99%

Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems

Zou

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

An arithmetic word problem typically includes a textual description containing several constant quantities. The key to solving the problem is to reveal the underlying mathematical relations (such as addition and subtraction) among quantities, and then generate equations to find solutions. This work presents a novel approach, Quantity Tagger, that automatically discovers such hidden relations by tagging each quantity with a sign corresponding to one type of mathematical operation. For each quantity, we assume there exists a latent, variable-sized quantity span surrounding the quantity token in the text, which conveys information useful for determining its sign. Empirical results show that our method achieves 5 and 8 points of accuracy gains on two datasets respectively, compared to prior approaches.

show abstract

Parsing Algebraic Word Problems into Equations

Cited by 169 publications

References 20 publications

NumNet: Machine Reading Comprehension with Numerical Reasoning

NumNet: Machine Reading Comprehension with Numerical Reasoning

EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference

Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems

Contact Info

Product

Resources

About