mr. majdi owda, dr. zuhair bandar, dr. keeley crockett
DESCRIPTION
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. Background to Research. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/1.jpg)
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.
![Page 2: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/2.jpg)
Background to Research• Databases
– Hierarchal Databases– Relational Databases *– Object Oriented Databases
• Artificial Intelligence– Knowledge Representation
• Knowledge Trees *– Expert Systems– Natural Language Processing
• Conversational Agents *– Machine Learning
• Human-Computer Interaction– Natural Language Interfaces *
![Page 3: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/3.jpg)
![Page 4: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/4.jpg)
![Page 5: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/5.jpg)
• Introduction– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 6: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/6.jpg)
Contents • Introduction
– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 7: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/7.jpg)
Natural Language Interfaces to Databases
• Where the Complexity comes from !!
• Past Approaches– Pattern-Matching– Intermediate Language – Syntax-Based Family – Semantic-Grammar
The Problem: Creating Reliable Natural Language Interfaces to Relational Databases.
![Page 8: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/8.jpg)
Contents • Introduction
– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 9: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/9.jpg)
Guided Conversation Agents• Alan Turing (Turing Test) 1950• Joseph Weizenbaum (Eliza) 1960s• Colboy (Parry) late 1960s • Wallace (Alice) 2000• MMU (InfoChat-Adam) 2001
Idea: use a guided conversational agent for NLIDBs. Algorithm: having a guided conversational agent component
trained to converse within a database domain knowledge.
![Page 10: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/10.jpg)
Guided Conversation Agents – 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
![Page 11: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/11.jpg)
Contents • Introduction
– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 12: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/12.jpg)
Knowledge Trees
Idea: using knowledge trees for NLIDBs.
Algorithm: having knowledge trees component within the new framework.
Direction Node
Goal Node
![Page 13: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/13.jpg)
Knowledge Trees Benefits
• Easy way to revise and maintain the knowledge base
• Overcome the lacking of connectivity between CA and the Relational Database
• Road map for the conversational agent dialogue flow
• Direct the conversational agent towards the goal.
![Page 14: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/14.jpg)
Contents • Introduction
– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 15: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/15.jpg)
Conversation-Based NLI-RDB Framework
• Main components– Conversational Agents
– Knowledge Trees
– Conversation Manager
– Relational Database
Relational Database
KnowledgeTree
SQL statements
Context Script files
Conversational Agent
Rule Matching
Conversation Manager
Context Switching & Manage
Agent Response
Response Generation
User Query
Information Extraction
![Page 16: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/16.jpg)
Contents • Introduction
– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 17: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/17.jpg)
Conversation-Based NLI-RDB Prototype Tools
![Page 18: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/18.jpg)
Conversation-Based NLI-RDB Interface
![Page 19: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/19.jpg)
Conversation-Based NLI-RDB Interface
![Page 20: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/20.jpg)
Contents • Introduction
– Natural Language Interfaces to Databases– Guided Conversational Agents– Knowledge Trees
• Proposed Framework
• Developed Prototype
• Conclusions and Future Work
• Q/A
![Page 21: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/21.jpg)
Conclusions• 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
![Page 22: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/22.jpg)
Current & Future Work
Idea: There is still big room to do further research.
• An adaptive conversation-based NLIDB
• Dynamic knowledge trees
![Page 23: Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley Crockett](https://reader036.vdocuments.us/reader036/viewer/2022081508/5681472c550346895db4658a/html5/thumbnails/23.jpg)
Special thanks “MMU Research Team”
Dr. Keeley Crockett Mr James O’Shea
Dr. Zuhair Bandar Dr. David Mclean