ABSTRACT
This chapter discusses the notion of language understanding and how it relates to Artificial Intelligence. It reviews some of the more important work on the theoretical side in the design of computer systems intended to understand natural language. The chapter presents a view on directions in the computational modelling of language understanding that seem most important for the near future. Language understanding systems are designed so as to produce symbolic structures supposed to represent meaning, so-called "meaning representations". R. Montague's work has popularized the use of expressions in a formal, logical language as semantic representations. Understanding a natural-language expression would change the state of the system; for instance, understanding the question should bring the system into a state where it knows that the speaker wants to know the value of the corresponding semantic representation. Speech act theory distinguishes a perlocutionary dimension of language use, which concerns the effects that a linguistic act altogether achieves.
