George E. Heidorn

Learn More
Dictionaries are rich sources of detailed semantic information , but in order to use the information for natural language processing, it must be organized systematically. This paper describes automatic and semi-automatic procedures for extracting and organizing semantic fea= ture information implicit in dictionary definitions. Two head-finding heuristics(More)
This is the first and final collection of a noteworthy set of research papers, which is both historical and timely. PLNLP, the Programming Language for Natural Language Processing, which emerged at IBM's Thomas J. Watson Research Center in Yorktown Heights about 15 years ago, is ostensibly the glue that holds the volume's 22 chapters together. But it is as(More)
gent " functions f o r processing business correspondence and other texts in an ofice environment. This paper focuses on the initial objectives of the system: critiquing written material on points of grammar and style. The overall system is described, with some details of the implementation, the user interface, and the three levels of processing, especially(More)
Processing syntactically ill-formed language is an important mission of the EPISTLE system, lll-formed input is treated by this system in various ways. Misspellings are highlighted by a standard spelling checker; syntactic errors are detected and corrections are suggested; and stylistic infelicities are called to the user's attention. Central to the EPISTLE(More)
The experimental EPISTLE system is ultimately intended to provide office workers with intelligent applications for the processing of natural language text, particularly business correspondence. A variety of possible critiques of textual material are identified in this paper, but the discussion focuses on the system's capability to detect several classes of(More)
A technique is described for performing fitted parsing. After the rules of a more conventional syntactic grammar are unable to produce a parse for an input string, this technique can be used to produce a reasonable approximate parse that can serve as input to the remaining stages of processing. The paper describes how fitted parsing is done in the EP[STLE(More)
This paper describes a project for studying the feasibility of developing systems which accomplish typical office tasks by means of human-like communication with the user. An actual dialogue with the initial version of a system that is being built for scheduling activities such as meetings is presented and then is used as a source of examples in explaining(More)