D
David Yarowsky
Researcher at Johns Hopkins University
Publications - 138
Citations - 13453
David Yarowsky is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Machine translation & Parsing. The author has an hindex of 50, co-authored 135 publications receiving 12678 citations. Previous affiliations of David Yarowsky include AT&T & Bell Labs.
Papers
More filters
Proceedings ArticleDOI
Unsupervised word sense disambiguation rivaling supervised methods
TL;DR: An unsupervised learning algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations.
Proceedings ArticleDOI
Word-sense disambiguation using statistical models of Roget's categories trained on large corpora
TL;DR: A program that disambiguates English word senses in unrestricted text using statistical models of the major Roget's Thesaurus categories, enabling training on unrestricted monolingual text without human intervention.
Proceedings ArticleDOI
Classifying latent user attributes in twitter
TL;DR: A novel investigation of stacked-SVM-based classification algorithms over a rich set of original features, applied to classifying these four user attributes, as distinct from the other primarily spoken genres previously studied in the user-property classification literature.
Journal ArticleDOI
A method for disambiguating word senses in a large corpus
TL;DR: The proposed method was designed to disambiguate senses that are usually associated with different topics using a Bayesian argument that has been applied successfully in related tasks such as author identification and information retrieval.
Proceedings ArticleDOI
One sense per discourse
TL;DR: An experiment confirmed the hypothesis that if a polysemous word such as sentence appears two or more times in a well-written discourse, it is extremely likely that they will all share the same sense and found that the tendency to share sense in the same discourse is extremely strong.