Question answering using evolving networks
Date of Publication
2004
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Computer Science
Subject Categories
Computer Sciences
College
College of Computer Studies
Department/Unit
Computer Science
Thesis Adviser
Shirley Barrido
Defense Panel Member
Ted Yap
Danny Cheng
Abstract/Summary
This study involves the exploration of evolving networks as a viable machine learning approach for question answering systems. Question answering systems engage in analyzing a free text, accepting questions and giving answers based on the input text. There are various works involving question answering systems using rule-based approaches and machine learning approaches. This research extends the work on question answering using machine-learning approaches by using evolving networks. The basic idea of evolving networks to improve performance. Three evolving network approaches on a back-propagation neural network were explored, namely, weights evolution, learning parameters evolution, and architecture evolution. The accuracy of each evolving network approach was benchmarked vis-a-vis other related works on question answering systems and was found to yield performance that is at par with the best performing approaches and in some instances, incrementally better. Thus, the evolving network approach is found to be a viable and competitive machine learning approach for question answering systems.
Abstract Format
html
Language
English
Format
Accession Number
TU13009
Shelf Location
Archives, The Learning Commons, 12F, Henry Sy Sr. Hall
Physical Description
1 v. (various foliations) : ill. (some col.) ; 28 cm.
Keywords
Machine learning; Algorithms; Question-answering systems
Recommended Citation
See, S. L., Sih, M. S., Tacderas, B. F., & Teo, M. G. (2004). Question answering using evolving networks. Retrieved from https://animorepository.dlsu.edu.ph/etd_bachelors/14111