Learning a spelling error model from search query logs Export

@inproceedings{citeulike:3609356, abstract = {Applying the noisy channel model to search query spelling correction requires an error model and a language model. Typically, the error model relies on a weighted string edit distance measure. The weights can be learned from pairs of misspelled words and their corrections. This paper investigates using the Expectation Maximization algorithm to learn edit distance weights directly from search query logs, without relying on a corpus of paired words.}, address = {Morristown, NJ, USA}, author = {Ahmad, Farooq and Kondrak, Grzegorz}, booktitle = {HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing}, citeulike-article-id = {3609356}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1220695}, citeulike-linkout-1 = {http://dx.doi.org/10.3115/1220575.1220695}, doi = {10.3115/1220575.1220695}, keywords = {approximate-search, spelling-correction, term-disambiguation}, location = {Vancouver, British Columbia, Canada}, pages = {955--962}, posted-at = {2008-11-20 13:31:28}, priority = {2}, publisher = {Association for Computational Linguistics}, title = {Learning a spelling error model from search query logs}, url = {http://dx.doi.org/10.3115/1220575.1220695}, year = {2005} }

TY - CONF ID - citeulike:3609356 L3 - citeulike-article-id:3609356 N2 - Applying the noisy channel model to search query spelling correction requires an error model and a language model. Typically, the error model relies on a weighted string edit distance measure. The weights can be learned from pairs of misspelled words and their corrections. This paper investigates using the Expectation Maximization algorithm to learn edit distance weights directly from search query logs, without relying on a corpus of paired words. CY - Vancouver, British Columbia, Canada AD - Morristown, NJ, USA EP - 962 TI - Learning a spelling error model from search query logs PB - Association for Computational Linguistics T2 - HLT '05: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing SP - 955 KW - approximate-search KW - spelling-correction KW - term-disambiguation AU - Ahmad, Farooq AU - Kondrak, Grzegorz PY - 2005/// UR - http://dx.doi.org/10.3115/1220575.1220695 ER -