Word meaning in context : a probabilistic model and its application to question answering
Georgiana Dinu · 2011
The need for assessing similarity in meaning is central to most language tech-nology applications. Distributional methods are robust, unsupervised methods which achieve high performance on this task. These methods measure similarity of word types solely based on patterns of word occurrences in large corpora, fol-lowing the intuition that similar words occur in similar contexts. As most Nat-ural Language Processing (NLP) applications deal with disambiguated words, words occurring in context, rather than word types, the question of adapting distributional methods to compute sense-specific or context-sensitive similari-ties has gained increasing attention in recent work. This thesis focuses on the development and applications of distributional meth-ods for context-sensitive similarity. The contribution made is twofold: the main part of the thesis proposes and tests a new framework for computing similarity in context, while the second part investigates the application of distributional paraphrasing to the task of question answering.