The subject of Natural Language Processing can be considered in both broad and narrow senses. In the broad sense, it covers processing issues at all levels of natural language understanding, including speech recognition, syntactic and semantic analysis of sentences, reference to the discourse context (including anaphora, inference of referents, and more extended relations of discourse coherence and narrative structure), conversational inference and implicature, and discourse planning and generation. In the narrower sense, it covers the syntactic and semantic processing sentences to deliver semantic objects suitable for referring, inferring, and the like. Of course, the results of inference and reference may under some circumstances play a part in processing in the narrow sense. But the processes that are characteristic of these other modules are not the primary concern.