Real-Word Error Correction with Trigrams: Correcting Multiple Errors in a Sentence

TL;DR

This paper introduces a novel approach for correcting multiple real-word errors in sentences using a PCFG-based model, demonstrating improved accuracy over previous methods on the Wall Street Journal corpus.

Contribution

It proposes a new variation of real-word error correction that effectively detects and corrects multiple errors by manipulating a Probabilistic Context-Free Grammar.

Findings

Outperforms WordNet-based correction method

Better than fixed window size approaches

Effective on Wall Street Journal corpus

Abstract

Spelling correction is a fundamental task in Text Mining. In this study, we assess the real-word error correction model proposed by Mays, Damerau and Mercer and describe several drawbacks of the model. We propose a new variation which focuses on detecting and correcting multiple real-word errors in a sentence, by manipulating a Probabilistic Context-Free Grammar (PCFG) to discriminate between items in the search space. We test our approach on the Wall Street Journal corpus and show that it outperforms Hirst and Budanitsky's WordNet-based method and Wilcox-O'Hearn, Hirst, and Budanitsky's fixed windows size method.-O'Hearn, Hirst, and Budanitsky's fixed windows size method.