Learning to Automatically Solve Algebra Word Problems

Nate Kushman; Yoav Artzi; Luke Zettlemoyer; Regina Barzilay

doi:10.3115/v1/p14-1026

Abstract

We present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a sys-tem of linear equations, while simultane-ously recovering an alignment of the vari-ables and numbers in these equations to the problem text. The learning algorithm uses varied supervision, including either full equations or just the final answers. We evaluate performance on a newly gathered corpus of algebra word problems, demon-strating that the system can correctly an-swer almost 70 % of the questions in the dataset. This is, to our knowledge, the first learning result for this task. 1

Keywords

Computer scienceWord (group theory)Algebra over a fieldWord problem (mathematics education)Artificial intelligenceNatural language processingArithmeticLinguisticsMathematicsPure mathematics

Affiliated Institutions

Related Publications

Deep Contextualized Word Representations

Matthew E. Peters , Mark E Neumann , Mohit Iyyer +4 more

We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses ...

2018 Proceedings of the 2018 Conference of... 1786 citations

Distributional Memory: A General Framework for Corpus-Based Semantics

Marco Baroni , Alessandro Lenci

Research into corpus-based semantics has focused on the development of ad hoc models that treat single tasks, or sets of closely related tasks, as unrelated challenges to be tac...

2010 Computational Linguistics 652 citations

MizAR 60 for Mizar 50

Ashish Vaswani , Noam Shazeer , Niki Parmar +5 more

As a present to Mizar on its 50th anniversary, we develop an AI/TP system that automatically proves about 60% of the Mizar theorems in the hammer setting. We also automatically ...

2023 Leibniz-Zentrum für Informatik (Schlo... 70225 citations

Supervised Learning of Universal Sentence Representations from Natural\n Language Inference Data

Alexis Conneau , Douwe Kiela , Holger Schwenk +2 more

Many modern NLP systems rely on word embeddings, previously trained in an\nunsupervised manner on large corpora, as base features. Efforts to obtain\nembeddings for larger chunk...

2017 arXiv (Cornell University) 2038 citations

The Use of Worked Examples as a Substitute for Problem Solving in Learning Algebra

John Sweller , Graham Cooper

The knowledge required to solve algebra manipulation problems and procedures designed to hasten knowledge acquisition were studied in a series of five experiments. It was hypoth...

1985 Cognition and Instruction 1156 citations

Publication Info

Year: 2014
Type: article
Citations: 356
Access: Closed

External Links

Download PDF (Free) View on DOI.org Semantic Scholar

Social Impact

Altmetric

Learning to Automatically Solve Algebra Word Problems

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

356

OpenAlex

Influential

120

CrossRef

Cite This

APA Style

                            
                                    Nate Kushman, 
                                
                                    Yoav Artzi, 
                                
                                    Luke Zettlemoyer
                                
                                et al.
                            
                            (2014). 
                            Learning to Automatically Solve Algebra Word Problems. 
                            Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
                            
                            .
                            https://doi.org/10.3115/v1/p14-1026

Identifiers

DOI: 10.3115/v1/p14-1026

Data Quality

Data completeness: 81%