Learning phrase-based spelling error models from clickthrough data
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Developing a corpus of plagiarised short answers
Language Resources and Evaluation
Hi-index | 0.00 |
In this paper we present the accuracy gains that spell corrector systems can provide to the plagiarism detection task when the appropriations contain spelling mistakes. These may have been introduced on purpose to avoid detection systems from finding the aforementioned appropriations, which could happen specially if such systems are based on lexical similarities. This document will detail the components that we have developed for both plagiarism detection and spell correction, and the significant gains that their combination produces.