IIIT Hyderabad Publications |
|||||||||
|
Deep Neural Network based system for solving Arithmetic Word problemsAuthors: Purvanshi Mehta,Pruthwik Mishra,Vinayak Sanjay Athavale,Manish Shrivastava,Dipti Misra Sharma Conference: 8th International Joint Conference on Natural Language Processing (IJCNLP-2017 2017) Location Taipei, Taiwan Date: 2017-11-27 Report no: IIIT/TR/2017/93 AbstractThis paper presents DILTON, a system which solves simple arithmetic word problems. DILTON first predicts the operation that is to be performed (’-’,’+’,’*’,’/’) through a deep neural network based model and then uses it to generate the answer. DILTON divides the question into two parts - worldstate and query as shown in Figure 1. The worldstate and the query are processed separately in two different networks and finally the networks are merged to predict the final operation. DILTON learns to predict operations with 88.81 % in a corpus of primary school questions. With simple similarity between the contexts of quantities appearing in the problem and the question text, we are able to identify 92.25 % of relevant quantities and solve 81% of the questions. Our code and data is publicly available. Full paper: pdf Centre for Language Technologies Research Centre |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |