Context-dependent reasoning with lexical knowledge using default logic

Lexical knowledge is increasingly important in language engineering. However, it is a dii-cult kind of knowledge to represent and reason with. Existing approaches to formalizing lexical knowledge have used languages with limited expressibility and in particular they have not addressed the context-dependent nature of lexical knowledge. Here we present a framework, based on default logic, called the dex framework, for capturing context-dependent reasoning with lexical knowledge. Default logic is a rst-order logic ooering a more expressive formali-sation than inheritance hierarchies: (1) First-order formulae about words can be inferred; (2) Preferences over formulae can be based on speciicity, reasoning about exceptions, or explicit priorities; (3) Contexts can be reasoned with as rst formulae; and (4) Contexts can be derived as default inferences. In the dex framework, the word for which further information is sought called the query word. The context for a query word is derived from further words, such as words in the same sentence as the query word. These further words are used with a form of decision tree called a context classiication tree to identify which contexts hold for the query word. We show how we can use these contexts in default logic to identify lexical knowledge about the query word such as synonyms, antinyms, specializations, meronyms, and more sophisticated rst-order semantic knowledge. We also show how we can use a standard machine learning algorithm for decision trees to generate context classiication trees.