Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Data collection for new conversational dialogue system

A dialogue system and dialogue technology, applied in data classification, processing input data, electronic digital data processing, etc., can solve problems such as unproven dialogue system, low exchange efficiency, and development difficulties

Pending Publication Date: 2019-06-14
MICROSOFT TECH LICENSING LLC
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This leads to extremely inefficient exchanges for uninformed users, as the system is limited by the idiosyncrasies of the development engineer
can be bootstrapped from this actual system (given that some form of machine learning is available to include previously unseen elements in the system), but the development of such a system is difficult
The current popular chatbots have not proven to be the progenitors of successful conversational systems

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
  • Data collection for new conversational dialogue system
  • Data collection for new conversational dialogue system
  • Data collection for new conversational dialogue system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present technology, loosely described, is a data collection system based on a set of generic dialog acts derived from a database schema. Crowdworkers perform two types of tasks: (i) identify meaningful dialogue paths, and (ii) perform context-sensitive paraphrasing of these dialogue paths to real dialogues. The final output of the system is a set of training examples of real dialogue annotated with its logical form. This data can be used to train all three components of the dialogue system: (i) a semantic parser for understanding context-sensitive utterances, (ii) a dialogue policy for generating new dialogue acts given the current state, and (iii) A generative system for deciding what to say and how to express it in natural language.

[0035] introduce

[0036] In some cases, the data generation system of the present technology may generate multiple canonical utterances from the logical form and associate annotations with the multiple canonical utterances. Annot...

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

A data collection system is based on a general set of dialogue acts which are derived from a database schema. Crowd workers perform two types of tasks: (i) identification of sensical dialogue paths and (ii) performing context-dependent paraphrasing of these dialogue paths into real dialogues. The end output of the system is a set of training examples of real dialogues which have been annotated with their logical forms. The data can be used to train all three components of the dialogue system: (i) the semantic parser for understanding context-dependent utterances, (ii) the dialogue policy for generating new dialogue acts given the current state, and (iii) the generation system for both deciding what to say and how to render it in natural language.

Description

Background technique [0001] Fluent conversational systems are difficult to design. The complexity of natural language coupled with a great deal of individual freedom of expression makes it difficult to design normative natural language interfaces such that they cover the potential interaction space. In addition, such a system that can do all the tasks in a specific topic is very difficult to use, because it cannot analyze various sentences spoken by the user, nor can it capture the action and language possibilities produced by the system. [0002] The problem is a chicken and egg problem - the system can use the Wizard of Oz (WOZ, Wizard of Oz) system to create a model of the conversational system, and then convince a large number of human users to interact with the system. This is expensive because the "conversational system" must be represented by human operators, and it is also limited to operating in the space of human operator utterances (each with idiosyncratic utteranc...

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): G06F17/27G06F40/20
CPCG10L15/063G10L15/22G10L2015/0638G06F40/20G06F40/169G06F40/30G06F40/205G06F3/0482G06F7/08G06N20/00
Inventor P·S·梁D·克莱恩L·吉利克J·科亨L·K·阿瑟诺J·克劳斯曼A·鲍尔斯D·霍尔
Owner MICROSOFT TECH LICENSING LLC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com