Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge
Abstract
We present a learning architecture for lexical semantic classification problems that supplements task-specific training data with background data encoding general "world knowledge". The model compiles knowledge contained in a dictionaryontology into additional training data, and integrates task-specific and background data through a novel hierarchical learning architecture. Experiments on a word sense disambiguation task provide empirical evidence that this "hierarchical classifier" outperforms a state-of-the-art standard "flat " one. 1
Cite
Text
Ciaramita et al. "Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge." International Joint Conference on Artificial Intelligence, 2003.Markdown
[Ciaramita et al. "Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge." International Joint Conference on Artificial Intelligence, 2003.](https://mlanthology.org/ijcai/2003/ciaramita2003ijcai-hierarchical/)BibTeX
@inproceedings{ciaramita2003ijcai-hierarchical,
title = {{Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge}},
author = {Ciaramita, Massimiliano and Hofmann, Thomas and Johnson, Mark},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2003},
pages = {817-822},
url = {https://mlanthology.org/ijcai/2003/ciaramita2003ijcai-hierarchical/}
}