Guided Conversational Agents and Knowledge Trees for Natural Language Interfaces to Relational Datab...
Download
1 / 19

Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett - PowerPoint PPT Presentation


  • 118 Views
  • Uploaded on

Guided Conversational Agents and Knowledge Trees for Natural Language Interfaces to Relational Databases. Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett The Intelligent Systems Group, Department of Computing and Mathematics, Manchester Metropolitan University. Introduction

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett ' - brigette-abdiel


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

Guided Conversational Agents and Knowledge Trees for Natural Language Interfaces to Relational Databases

Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett

The Intelligent Systems Group, Department of Computing and Mathematics, Manchester Metropolitan University.


  • Introduction Language Interfaces to Relational Databases

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


Contents Language Interfaces to Relational Databases

  • Introduction

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


Natural Language Interfaces to Databases Language Interfaces to Relational Databases

  • Where the Complexity comes from !!

  • Past Approaches

    • Pattern-Matching

    • IntermediateLanguage

    • Syntax-Based Family

    • Semantic-Grammar

The Challenge: Creating Simple & Reliable Natural Language Interfaces to Relational Databases.


Contents Language Interfaces to Relational Databases

  • Introduction

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


Conversation Agents Language Interfaces to Relational Databases

  • Initial Idea -- Alan Turing (Turing Test) 1950

  • First System -- Joseph Weizenbaum (Eliza) 1960s

  • 1st Robust System -- Colboy (Parry) late 1960s

  • 1st reusable, general purpose system -- Wallace (Alice) 2000

  • MMU (InfoChat-Adam) 2001

Idea: use a guided conversational agent for NLIDBs.


Guided Conversation Agents Language Interfaces to Relational Databases– Why InfoChat

  • Autonomous general purpose CA

  • Deals set of contexts

  • Direct the users towards a goal

  • Flexible and robust

  • Converse freely within a specific domain

  • Extract, manipulate, and store information


Contents Language Interfaces to Relational Databases

  • Introduction

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


Knowledge Trees Language Interfaces to Relational Databases

  • Easy to revise & maintain

  • connect CA & R-DB

  • Road map for CA dialogue flow

  • Direct CA towards the goal

Direction Node

Goal Node

Idea: using knowledge trees for NLIDBs.


Contents Language Interfaces to Relational Databases

  • Introduction

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


User Query Language Interfaces to Relational Databases

Agent Response

Conversation Manager

Response Generation

Context Switching & Manage

Knowledge

Tree

Conversational Agent

SQL statements

Rule Matching

Information Extraction

Context Script files

Relational Database

Conversation-Based NLI-RDB Framework

  • Main components

    • Conversational Agents

    • Knowledge Trees

    • Conversation Manager

    • Relational Database


Contents Language Interfaces to Relational Databases

  • Introduction

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


Conversation-Based NLI-RDB Interface Tools Language Interfaces to Relational Databases– Knowledge Tree Builder


Conversation-Based NLI-RDB Interface Tools Language Interfaces to Relational Databases– User Interface


Conversation-Based NLI-RDB Interface Tools Language Interfaces to Relational Databases– User Interface


Contents Language Interfaces to Relational Databases

  • Introduction

    • Natural Language Interfaces to Databases

    • Guided Conversational Agents

    • Knowledge Trees

  • Proposed Framework

  • Developed Interface Tools

  • Conclusions and Future Work

  • Q/A


Conclusions Language Interfaces to Relational Databases

  • Easy and flexible way in order to develop a Conversation-Based NLI-RDB

  • General purpose framework which can be applied to a wide range of domains

  • Utilizing dialogue interaction

  • Knowledge trees are easy to create, structure, update, revise, and maintain

  • Capability of handling simple and complex queries


Current & Future Work Language Interfaces to Relational Databases

  • An adaptive conversation-based NLIDB

  • Dynamic knowledge trees

Idea: There is still big room to do further research. 


Questions Language Interfaces to Relational Databases

[email protected]


ad