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

Wang, Ling; Yogatama, Dani; Dyer, Chris; Blunsom, Phil

doi:10.18653/v1/p17-1015

Cited by 208 publications

(278 citation statements)

References 12 publications

Supporting

Mentioning

276

Contrasting

Order By: Relevance

“…Our work is also related to recent studies on model interpretation (Ribeiro et al, 2016;Lipton, 2016;Ling et al, 2017). Recently, much work has paid attention to giving textual explanations for classifications.…”

Section: Related Workmentioning

confidence: 65%

Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions

Hai¹,

Jiang²,

Luo³

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

112

View full text Add to dashboard Cite

In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-to-text natural language generation (NLG) problem. Sequenceto-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.

show abstract

Section: Related Workmentioning

confidence: 65%

Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions

Hai¹,

Jiang²,

Luo³

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

112

View full text Add to dashboard Cite

show abstract

“…Dataset: Math23K 1 collected by Wang et al (2017) problems are linear algebra questions with only one unknown variable. Baselines: We compare our methods with two baselines: DNS and DNS-Hybrid.…”

Section: Methodsmentioning

confidence: 99%

Translating a Math Word Problem to a Expression Tree

Wang¹,

Wang²,

Cai³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

124

View full text Add to dashboard Cite

Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one equations. This non-deterministic transduction harms the performance of maximum likelihood estimation. In this paper, by considering the uniqueness of expression tree, we propose an equation normalization method to normalize the duplicated equations. Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving. We find that each model has its own specialty in solving problems, consequently an ensemble model is then proposed to combine their advantages. Experiments on dataset Math23K show that the ensemble model with equation normalization significantly outperforms the previous state-of-the-art methods.

show abstract

“…formalized the AWP problem as that of generating and scoring equation trees via integer linear programming. Wang et al (2017b) and Ling et al (2017) proposed sequence to sequence solvers for the AWP problems, which are capable of generating unseen expressions and do not rely on sophisticated manual features. Wang et al (2018) leveraged deep Q-network to solve the AWP problems, achieving a good balance between effectiveness and efficiency.…”

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

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

Cited by 208 publications

References 12 publications

Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions

Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions

Translating a Math Word Problem to a Expression Tree

NumNet: Machine Reading Comprehension with Numerical Reasoning

Contact Info

Product

Resources

About