Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Natural language processing of disfluent sentences

A technology of spoken language and words, applied in natural language data processing, electrical digital data processing, special data processing applications, etc., can solve problems such as it is difficult to know the neglect of spoken language instructions

Active Publication Date: 2012-05-30
ROBERT BOSCH GMBH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] But even with the ability to turn spoken sounds into text words with great accuracy, the computer controlling the oven has a hard time knowing which parts of spoken instructions to ignore

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Natural language processing of disfluent sentences
  • Natural language processing of disfluent sentences
  • Natural language processing of disfluent sentences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] figure 1 The natural language processing system 100 is schematically represented. The system interprets spoken word input (such as sentence fragments 102) and outputs codes that a computer can understand (such as machine instructions 104). The overall system allows a human to speak directly to a computer in normal human language.

[0019] The main components of system 100 are speech recognition unit 110 , part of speech marker 112 , disfluency identifier 114 and grammar parser 118 . The disfluency discriminator operates using the model 116 .

[0020] The speech recognition unit 110 transcribes a human speech sound into text data. This text is then sent to a part of speech tagger 112 which labels each text word with a part of speech (POS) tag such as "noun", "verb", etc. The text annotated with POS tags is input to the disfluency identifier 114 . The disfluency discriminator and its model 116 decide which words should be clipped and ignored from the text for improve...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An advanced model that includes new processes is provided for use as a component of an effective disfluency identifier. The disfluency identifier tags edited words in transcribed speech. A speech recognition unit in combination with a part-of-speech tagger, a disfluency identifier, and a parser form a natural language system that helps machines properly interpret spoken utterances.

Description

technical field [0001] Generally, the present invention relates to natural language processing. In particular, it deals with handling unfluent sentences. Background technique [0002] Natural language processing is the science of getting computers to interpret instructions or information the way humans do. Now consider the task of setting the oven temperature as an example. Practically anyone can understand the spoken command "set the oven to three hundred and fifty degrees (set the oven to 350 degrees)". And people totally understand some variations, like, "set the umm burner, I mean oven, to three hundred and fifty degrees" or, "set the oven to, you know, like three hundred and fifty degrees (position the oven, you know, about 350 degrees)". [0003] But even if it could turn spoken sounds into text words with great accuracy, the computer controlling the oven would have a hard time knowing which parts of spoken instructions to ignore. How exactly should a computer int...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/28G06F40/00
CPCG10L15/1822G10L15/19
Inventor 翁富良张奇
Owner ROBERT BOSCH GMBH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products