d abstract) John Longley Laboratory for Foundations of Computer Science School of Informatics, University of Edinburgh The King's Buildings, Mayfield Road Edinburgh EH9 3JZ, U...
The rapid growth of geotagged social media raises new computational possibilities for investigating geographic linguistic variation. In this paper, we present a multi-level genera...
Jacob Eisenstein, Brendan O'Connor, Noah A. Smith,...
We present Promodes, an algorithm for unsupervised word decomposition, which is based on a probabilistic generative model. The model considers segment boundaries as hidden variable...
The purpose of this study is to propose a new method for machine translation. We have proceeded through with two projects for report generation (Kittredge and Polguere, 2000) : We...
Word Sense Disambiguation (WSD) often relies on a context model or vector constructed from the words that co-occur with the target word within the same text windows. In most cases...
Bernard Brosseau-Villeneuve, Jian-Yun Nie, Noriko ...