Most previous corpus-based algorithms disambiguate a word with a classifier trained from previous usages of the same word. Separate classifiers have to be trained for different wo...
Abstract— In this paper we suggest a new approach to represent text document collections, integrating background knowledge to improve clustering effectiveness. Background knowled...
In this paper we investigate the challenges of applying statistical machine translation to meeting conversations, with a particular view towards analyzing the importance of modeli...
This article presents a new freely available trilingual corpus (Catalan, Spanish, English) that contains large portions of the Wikipedia and has been automatically enriched with l...
Samuel Reese, Gemma Boleda, Montse Cuadros, Llu&ia...
This paper addresses the issue of word-sense ambiguity in extraction from machine-readable resources for the construction of large-scale knowledge sources. We describe two experim...