Automatic Semantic Relation Extraction with Multiple Boundary Generation
Abstract
This paper addresses the task of automatic classification of semantic relations between nouns. We present an improved WordNet-based learning model which relies on the semantic information of the constituent nouns. The representation of each noun's meaning captures conceptual features which play a key role in the identification of the semantic relation. We report substantial improvements over previous WordNet-based methods on the 2007 SemEval data. Moreover, our experiments show that WordNet's IS-A hierarchy is better suited for some semantic relations compared with others. We also compute various learning curves and show that our model does not need a large number of training examples.
Cite
Text
Beamer et al. "Automatic Semantic Relation Extraction with Multiple Boundary Generation." AAAI Conference on Artificial Intelligence, 2008.Markdown
[Beamer et al. "Automatic Semantic Relation Extraction with Multiple Boundary Generation." AAAI Conference on Artificial Intelligence, 2008.](https://mlanthology.org/aaai/2008/beamer2008aaai-automatic/)BibTeX
@inproceedings{beamer2008aaai-automatic,
title = {{Automatic Semantic Relation Extraction with Multiple Boundary Generation}},
author = {Beamer, Brandon and Rozovskaya, Alla and Girju, Roxana},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2008},
pages = {824-829},
url = {https://mlanthology.org/aaai/2008/beamer2008aaai-automatic/}
}