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...
A central problem of word sense disambiguation (WSD) is the lack of manually sense-tagged data required for supervised learning. In this paper, we evaluate an approach to automati...
Given the recent trend to evaluate the performance of word sense disambiguation systems in a more application-oriented set-up, we report on the construction of a multilingual benc...
Two kinds of systems have been defined during the long history of WSD: principled systems that define which knowledge types are useful for WSD, and robust systems that use the info...
Linguists often represent the relationships between words in a collection of text as an undirected graph G = (V, E), were V is the vocabulary and vertices are adjacent in G if and...
Pranav Anand, Henry Escuadro, Ralucca Gera, Craig ...