Web-Scale N-Gram Models for Lexical Disambiguation
Abstract
Web-scale data has been used in a diverse range of language research. Most of this research has used web counts for only short, fixed spans of context. We present a unified view of using web counts for lexical disambiguation. Unlike previous approaches, our supervised and unsupervised systems combine information from multiple and overlapping segments of context. On the tasks of preposition selection and context-sensitive spelling correction, the supervised system reduces disambiguation error by 20-24% over the current state-of-the-art. Shane Bergsma, Dekang Lin, Randy Goebel
Cite
Text
Bergsma et al. "Web-Scale N-Gram Models for Lexical Disambiguation." International Joint Conference on Artificial Intelligence, 2009.Markdown
[Bergsma et al. "Web-Scale N-Gram Models for Lexical Disambiguation." International Joint Conference on Artificial Intelligence, 2009.](https://mlanthology.org/ijcai/2009/bergsma2009ijcai-web/)BibTeX
@inproceedings{bergsma2009ijcai-web,
title = {{Web-Scale N-Gram Models for Lexical Disambiguation}},
author = {Bergsma, Shane and Lin, Dekang and Goebel, Randy},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2009},
pages = {1507-1512},
url = {https://mlanthology.org/ijcai/2009/bergsma2009ijcai-web/}
}