@inproceedings{312ed9771a124cd6b7b12e2d98b44262,
title = "Exploiting syntactic and distributional information for spelling correction with web-scale N-gram models",
abstract = "We propose a novel way of incorporating dependency parse and word co-occurrence information into a state-of-the-art web-scale n-gram model for spelling correction. The syntactic and distributional information provides extra evidence in addition to that provided by a web-scale n-gram corpus and especially helps with data sparsity problems. Experimental results show that introducing syntactic features into n-gram based models significantly reduces errors by up to 12.4% over the current state-of-the-art. The word co-occurrence information shows potential but only improves overall accuracy slightly.",
author = "Wei Xu and Joel Tetreault and Martin Chodorow and Ralph Grishman and Le Zhao",
year = "2011",
language = "English (US)",
isbn = "1937284115",
series = "EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
pages = "1291--1300",
booktitle = "EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
note = "Conference on Empirical Methods in Natural Language Processing, EMNLP 2011 ; Conference date: 27-07-2011 Through 31-07-2011",
}