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...
An unsupervised method for word sense disambiguation using a bilingual comparable corpus was developed. First, it extracts statistically significant pairs of related words from th...
Graph-based methods have gained attention in many areas of Natural Language Processing (NLP) including Word Sense Disambiguation (WSD), text summarization, keyword extraction and ...
We develop latent Dirichlet allocation with WORDNET (LDAWN), an unsupervised probabilistic topic model that includes word sense as a hidden variable. We develop a probabilistic po...