pedersen

Word Sense Disambiguation is the problem of determining the meaning of a word based on the context in which it is used. This is a long-standing problem in Natural Language Processing (NLP), and is an important prerequisite to many other important NLP problems. In this work the researchers take a corpus-based approach, where patterns of word usage in large samples of text are analyzed. The goal is to identify instances of a word that occur in similar contexts, since these are often have very similar or identical meanings. The researchers have pursued vector space solutions to this problem, and they are now exploring the potential of word embeddings as a representation for the different senses of words. They are also extending this approach to apply to the problem of sentiment analysis, which is the problem of identifying the tone or opinion in a piece of text.