Patent · US Active

Language processing method and integrated circuit

US9472189B2 · kind B2 · utility

2Cited by
5References
13Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 15, 2013
Grant dateOct 18, 2016
Priority date
Expiry dateJul 10, 2034

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/19
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A parse unit parses an input sequence of token elements for an input string, wherein each token element contains a token and/or at least one corresponding token classifier. In a first mode the parse unit applies regular production rules on the token elements and on multi-token classifiers for phrases obtained from the token classifiers. If the first mode parsing does not result in a multi-token classifier encompassing all tokens of the input string, a control unit controls the parse unit to parse the input sequence in a second mode that applies both the regular and artificial production rules. A rule generator unit generates the artificial production rules based on the input sequence and/or intermediate results of the parsing. The parser unit provides a complete parse tree for ungrammatical sentences and a solution where the regular production rules do not cover the complete grammar of the respective natural language.

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