Natural Language Processing in an Automatic Programming Domain
Abstract
This paper is about communicating with computers in English. In particular, it describes an interface system which allows a human user to communicate with an automatic programming system in an English dialogue. The interface consists of two parts. The first is a parser called Reader. Reader was designed to facilitate writing English grammars which are nearly deterministic in that they consider a very small number of parse paths during the processing of a sentence. This efficiency is primarily derived from using a single parse structure to represent more than one syntactic interpretation of the input sentence. The second part of the interface is an interpreter which represents Reader's output in a form that can be used by a computer program without linguistic knowledge. The Interpreter is responsible for asking questions of the user, processing the user's replies, building a representation of the program the user's replies describe, and supplying the parser with any of the contextual information or general knowledge it needs while parsing.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 1978
- Accession Number
- ADA058531
Entities
People
- Jerrold M. Ginsparg
Organizations
- Stanford University