Patent · US Expired

Natural language processing system and method for parsing a plurality of input symbol sequences into syntactically or pragmatically correct word messages

US5299125A · kind A · utility

250Cited by
12References
83Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 8, 1993
Grant dateMar 29, 1994
Priority date
Expiry dateFeb 8, 2013

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/253
  • WIPO fieldControl
  • WIPO sectorInstruments

Abstract

A Natural Language Processing System utilizes a symbol parsing layer in combination with an intelligent word parsing layer to produce a syntactically or pragmatically correct output sentence or other word message. Initially, a plurality of polysemic symbol sequences are input through a keyboard segmented into a plurality of semantic, syntactic, or pragmatic segments including agent, action and patient segments, for example. One polysemic symbol sequence, including a plurality of polysemic symbols, is input from each of the three segments of the keyboard. A symbol parsing device, in a symbol parsing layer, then parses each of the plurality of symbols in each polysemic symbol sequence to access a previously stored word, morpheme, or phrase. The word, morpheme, or phrase is accessed which corresponds to the polysemic symbol sequence and further corresponds to one of the designated agent, action or patient segments. Each accessed word, morpheme, or phrase further accesses corresponding and previously stored grammatical and semantic information. An intelligent word parsing layer then receives and subsequently applies each of the plurality of words, morphemes, or phrases to a predetermin…

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.