In this paper, we propose a new method for semantic class induction. First, we introduce a generative model of sentences, based on dependency trees and which takes into account homonymy. Our model can thus be seen as a generalization of Brown clustering. Second, we describe an efficient algorithm to perform inference and learning in this model. Third, we apply our proposed method on two large d...

Apun is a form of wordplay in which aword suggests two or more meanings by exploiting polysemy, homonymy, or phonological similarity to another word, for an intended humorous or rhetorical effect. Though a recurrent and expected feature in many discourse types, puns stymie traditional approaches to computational lexical semantics because they violate their one-sense-percontext assumption. This ...

Current vector-space models of lexical semantics create a single “prototype” vector to represent the meaning of a word. However, due to lexical ambiguity, encoding word meaning with a single vector is problematic. This paper presents a method that uses clustering to produce multiple “sense-specific” vectors for each word. This approach provides a context-dependent vector representation of word ...

The generic name Furia (F. submissa Egorova and Shabanov, 1987, by original designation) was proposed by Egorova and Shabanov (1987, p. 74) for a new trilobite genus from the middle Cambrian of Yakutia, Siberia. However, this name is already preoccupied by Furia Linnaeus (1758, p. 644). To resolve homonymy, in accordance with the International Code of Zoological Nomenclature, Shabanovia nom. no...

The goal of the Portal da Língua Portuguesa project is to construe a set of lexical resources with a double objective. On the one hand, the resources serve as the content source for a web site about the Portuguese language, aimed at the general public. On the other hand, the resources are built to serve as an open source repository of lexical information for linguistic research. The design of t...