From Distributional to Semantic Similarity

Abstract

Lexical-semantic resources, including thesauri and WORDNET, have been successfully incorporated into a wide range of applications in Natural Language Processing. However they are very difficult and expensive to create and maintain, and their usefulness has been severely hampered by their limited coverage, bias and inconsistency. Automated and semi-automated methods for developing such resources are therefore crucial for further resource development and improved application performance. Systems that extract thesauri often identify similar words using the distributional hypothesis that similar words appear in similar contexts. This approach involves using corpora to examine the contexts each word appears in and then calculating the similarity between context distributions. Different definitions of context can be used, and I begin by examining how different types of extracted context influence similarity. To be of most benefit these systems must be capable of finding synonyms for rare words. Reliable context counts for rare events can only be extracted from vast collections of text. In this dissertation I describe how to extract contexts from a corpus of over 2 billion words. I describe techniques for processing text on this scale and examine the trade-off between context accuracy, information content and quantity of text analysed. Distributional similarity is at best an approximation to semantic similarity. I develop improved approximations motivated by the intuition that some events in the context distribution are more indicative of meaning than others. For instance, the object-of-verb context wear is far more indicative of a clothing noun than get. However, existing distributional techniques do not effectively utilise this information. The new context-weighted similarity metric I propose in this dissertation significantly outperforms every distributional similarity metric described in the literature. Nearest-neighbour similarity algorithms scale poorly with vocabulary and context vector size. To overcome this problem I introduce a new context-weighted approximation algorithm with bounded complexity in context vector size that significantly reduces the system runtime with only a minor performance penalty. I also describe a parallelized version of the system that runs on a Beowulf cluster for the 2 billion word experiments. To evaluate the context-weighted similarity measure I compare ranked similarity lists against gold-standard resources using precision and recall-based measures from Information Retrieval, since the alternative, application-based evaluation, can often be influenced by distributional as well as semantic similarity. I also perform a detailed analysis of the final results using WORDNET. Finally, I apply my similarity metric to the task of assigning words to WORDNET semantic categories. I demonstrate that this new approach outperforms existing methods and overcomes some of their weaknesses.