The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers

Zhang, Dongxiang; Wang, Lei; Zhang, Luming; Dai, Bing Tian; Shen, Heng Tao

doi:10.1109/tpami.2019.2914054

Cited by 89 publications

(50 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Math & Algebraic Word Problems: There is a wide literature on using machine learning to solve algebraic word problems (Ling et al, 2017;Roy and Roth, 2016;Zhang et al, 2019), building novel neural modules to directly learn numerical operations (Trask et al, 2018;Madsen and Johansen, 2020) and solving a variety of challenging mathematical problems (Saxton et al, 2019;Lee et al, 2020;Lample and Charton, 2020). In these tasks, numbers can be treated as symbolic variables and computation based on these values leverages a latent tree of arithmetic operations.…”

Section: Related Workmentioning

confidence: 99%

An Empirical Investigation of Contextualized Number Prediction

Berg-Kirkpatrick¹,

Spokoyny²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We conduct a large scale empirical investigation of contextualized number prediction in running text. Specifically, we consider two tasks: (1) masked number prediction -predicting a missing numerical value within a sentence, and (2) numerical anomaly detectiondetecting an errorful numeric value within a sentence. We experiment with novel combinations of contextual encoders and output distributions over the real number line. Specifically, we introduce a suite of output distribution parameterizations that incorporate latent variables to add expressivity and better fit the natural distribution of numeric values in running text, and combine them with both recurrent and transformer-based encoder architectures. We evaluate these models on two numeric datasets in the financial and scientific domain. Our findings show that output distributions that incorporate discrete latent variables and allow for multiple modes outperform simple flow-based counterparts on all datasets, yielding more accurate numerical prediction and anomaly detection. We also show that our models effectively utilize textual context and benefit from general-purpose unsupervised pretraining. 1

show abstract

Section: Related Workmentioning

confidence: 99%

An Empirical Investigation of Contextualized Number Prediction

Berg-Kirkpatrick¹,

Spokoyny²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Here we will introduce recent studies based on the Seq2Seq framework. The work presented in (Zhang et al, 2018) reviews more early approaches. (Wang et al, 2017) made the first attempt to directly generate equation expressions by using the Seq2Seq model and published a high-quality Chinese dataset Math23K.…”

Section: Related Workmentioning

confidence: 99%

“…The main drawbacks of these methods lie in their heavy dependency on manual features and incapacity to generate new templates for new problems. Consequently, they can only achieve satisfactory results on small-scale datasets (Zhang et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Solving Math Word Problems with Multi-Encoders and Multi-Decoders

Shen¹,

Jin²

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

Math word problems solving remains a challenging task where potential semantic and mathematical logic need to be mined from natural language. Although previous researches employ the Seq2Seq technique to transform text descriptions into equation expressions, most of them achieve inferior performance due to insufficient consideration in the design of encoder and decoder. Specifically, these models only consider input/output objects as sequences, ignoring the important structural information contained in text descriptions and equation expressions. To overcome those defects, a model with multi-encoders and multi-decoders is proposed in this paper, which combines sequence-based encoder and graph-based encoder to enhance the representation of text descriptions, and generates different equation expressions via sequence-based decoder and tree-based decoder. Experimental results on the dataset Math23K show that our model outperforms existing state-of-the-art methods.

show abstract

“…The findings imply that this line of research still has great room for improvement and calls for more general and robust solutions. For more comprehensive review on MWP solvers, readers can refer to a recent survey paper (Zhang et al 2018).…”

Section: Algebra Word Problem Solvermentioning

confidence: 99%

Template-Based Math Word Problem Solvers with Recursive Neural Networks

Wang

Zhang

et al. 2019

AAAI

Self Cite

View full text Add to dashboard Cite

The design of automatic solvers to arithmetic math word problems has attracted considerable attention in recent years and a large number of datasets and methods have been published. Among them, Math23K is the largest data corpus that is very helpful to evaluate the generality and robustness of a proposed solution. The best performer in Math23K is a seq2seq model based on LSTM to generate the math expression. However, the model suffers from performance degradation in large space of target expressions. In this paper, we propose a template-based solution based on recursive neural network for math expression construction. More specifically, we first apply a seq2seq model to predict a tree-structure template, with inferred numbers as leaf nodes and unknown operators as inner nodes. Then, we design a recursive neural network to encode the quantity with Bi-LSTM and self attention, and infer the unknown operator nodes in a bottom-up manner. The experimental results clearly establish the superiority of our new framework as we improve the accuracy by a wide margin in two of the largest datasets, i.e., from 58.1% to 66.9% in Math23K and from 62.8% to 66.8% in MAWPS.

show abstract

The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers

Cited by 89 publications

References 93 publications

An Empirical Investigation of Contextualized Number Prediction

An Empirical Investigation of Contextualized Number Prediction

Solving Math Word Problems with Multi-Encoders and Multi-Decoders

Template-Based Math Word Problem Solvers with Recursive Neural Networks

Contact Info

Product

Resources

About