Hypothetically, if you were told: Apple uses the apple as its logo . You would
immediately detect two different senses of the word apple , these being the
company and the fruit respectively. Making this distinction is the formidable
challenge of Word Sense Disambiguation (WSD), which is the subtask of
many Natural Language Processing (NLP) applications. This thesis is a
multi-branched investigation into WSD, that explores and evaluates unsupervised
knowledge-based methods that exploit semantic subgraphs. The
nature of research covered by this thesis can be broken down to:
1. Mining data from the encyclopedic resource Wikipedia, to visually
prove the existence of context embedded in semantic subgraphs
2. Achieving disambiguation in order to merge concepts that originate
from heterogeneous semantic graphs
3. Participation in international evaluations of WSD across a range of
languages
4. Treating WSD as a classification task, that can be optimised through
the iterative construction of semantic subgraphs
The contributions of each chapter are ranged, but can be summarised by
what has been produced, learnt, and raised throughout the thesis. Furthermore
an API and several resources have been developed as a by-product
of this research, all of which can be accessed by visiting the author’s home
page at http://www.stevemanion.com. This should enable researchers to
replicate the results achieved in this thesis and build on them if they wish.
| Identifer | oai:union.ndltd.org:canterbury.ac.nz/oai:ir.canterbury.ac.nz:10092/10016 |
| Date | January 2014 |
| Creators | Manion, Steve Lawrence |
| Publisher | University of Canterbury. Department of Mathematics & Statistics |
| Source Sets | University of Canterbury |
| Language | English |
| Detected Language | English |
| Type | Electronic thesis or dissertation, Text |
| Rights | Copyright Steve Lawrence Manion, http://library.canterbury.ac.nz/thesis/etheses_copyright.shtml |
| Relation | NZCU |
Page generated in 0.0022 seconds