James ate 5 oranges= Steve bought 5 pencils: Structure-Aware Denoising for Paraphrasing Word Problems

Rishabh Gupta*, V. Viswanathan, Mukesh Mohania, Vikram Goyal

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

We propose SCANING, an unsupervised framework for paraphrasing via controlled noise injection. We focus on the novel task of paraphrasing algebraic word problems having practical applications in online pedagogy as a means to reduce plagiarism as well as evoke reasoning capabilities on the part of the student instead of rote memorization. This task is more complex than paraphrasing general-domain corpora due to the difficulty in preserving critical information for solution consistency of the paraphrased word problem, managing the increased length of the text and ensuring diversity in the generated paraphrase. Existing approaches fail to demonstrate adequate performance on at least one, if not all, of these facets, necessitating the need for a more comprehensive solution. To this end, we model the noising search space as a composition of contextual and syntactic aspects to sample noising functions.
Original languageEnglish
Title of host publicationProceedings of the 32nd ACM International Conference on Information and Knowledge Management
Pages679-688
Number of pages10
Publication statusPublished - Aug 2023
Externally publishedYes

Fingerprint

Dive into the research topics of 'James ate 5 oranges= Steve bought 5 pencils: Structure-Aware Denoising for Paraphrasing Word Problems'. Together they form a unique fingerprint.

Cite this