Learning to use formulas to solve simple arithmetic problems

Arindam Mitra, Chitta Baral

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Solving simple arithmetic word problems is one of the challenges in Natural Language Understanding. This paper presents a novel method to learn to use formulas to solve simple arithmetic word problems. Our system, analyzes each of the sentences to identify the variables and their attributes; and automatically maps this information into a higher level representation. It then uses that representation to recognize the presence of a formula along with its associated variables. An equation is then generated from the formal description of the formula. In the training phase, it learns to score the <formula, variables> pair from the systematically generated higher level representation. It is able to solve 86.07% of the problems in a corpus of standard primary school test questions and beats the state-of-the-art by a margin of 8.07%.

Original languageEnglish (US)
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages2144-2153
Number of pages10
Volume4
ISBN (Electronic)9781510827585
StatePublished - 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: Aug 7 2016Aug 12 2016

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period8/7/168/12/16

Fingerprint

learning
primary school
language
Language Understanding
Natural Language
Equations
Primary School

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Mitra, A., & Baral, C. (2016). Learning to use formulas to solve simple arithmetic problems. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers (Vol. 4, pp. 2144-2153). Association for Computational Linguistics (ACL).

Learning to use formulas to solve simple arithmetic problems. / Mitra, Arindam; Baral, Chitta.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Vol. 4 Association for Computational Linguistics (ACL), 2016. p. 2144-2153.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mitra, A & Baral, C 2016, Learning to use formulas to solve simple arithmetic problems. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. vol. 4, Association for Computational Linguistics (ACL), pp. 2144-2153, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 8/7/16.
Mitra A, Baral C. Learning to use formulas to solve simple arithmetic problems. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Vol. 4. Association for Computational Linguistics (ACL). 2016. p. 2144-2153
Mitra, Arindam ; Baral, Chitta. / Learning to use formulas to solve simple arithmetic problems. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Vol. 4 Association for Computational Linguistics (ACL), 2016. pp. 2144-2153
@inproceedings{b879f59ec9a9452b85aad292e89f7b92,
title = "Learning to use formulas to solve simple arithmetic problems",
abstract = "Solving simple arithmetic word problems is one of the challenges in Natural Language Understanding. This paper presents a novel method to learn to use formulas to solve simple arithmetic word problems. Our system, analyzes each of the sentences to identify the variables and their attributes; and automatically maps this information into a higher level representation. It then uses that representation to recognize the presence of a formula along with its associated variables. An equation is then generated from the formal description of the formula. In the training phase, it learns to score the pair from the systematically generated higher level representation. It is able to solve 86.07{\%} of the problems in a corpus of standard primary school test questions and beats the state-of-the-art by a margin of 8.07{\%}.",
author = "Arindam Mitra and Chitta Baral",
year = "2016",
language = "English (US)",
volume = "4",
pages = "2144--2153",
booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Learning to use formulas to solve simple arithmetic problems

AU - Mitra, Arindam

AU - Baral, Chitta

PY - 2016

Y1 - 2016

N2 - Solving simple arithmetic word problems is one of the challenges in Natural Language Understanding. This paper presents a novel method to learn to use formulas to solve simple arithmetic word problems. Our system, analyzes each of the sentences to identify the variables and their attributes; and automatically maps this information into a higher level representation. It then uses that representation to recognize the presence of a formula along with its associated variables. An equation is then generated from the formal description of the formula. In the training phase, it learns to score the pair from the systematically generated higher level representation. It is able to solve 86.07% of the problems in a corpus of standard primary school test questions and beats the state-of-the-art by a margin of 8.07%.

AB - Solving simple arithmetic word problems is one of the challenges in Natural Language Understanding. This paper presents a novel method to learn to use formulas to solve simple arithmetic word problems. Our system, analyzes each of the sentences to identify the variables and their attributes; and automatically maps this information into a higher level representation. It then uses that representation to recognize the presence of a formula along with its associated variables. An equation is then generated from the formal description of the formula. In the training phase, it learns to score the pair from the systematically generated higher level representation. It is able to solve 86.07% of the problems in a corpus of standard primary school test questions and beats the state-of-the-art by a margin of 8.07%.

UR - http://www.scopus.com/inward/record.url?scp=85012031741&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012031741&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85012031741

VL - 4

SP - 2144

EP - 2153

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

PB - Association for Computational Linguistics (ACL)

ER -