An Ontology-based Approach to Text Summarization

Abstract

Extractive text summarization aims to create a condensed version of one or more source documents by selecting the most informative sentences. Research in text summarization has therefore often focused on measures of the usefulness of sentences for a summary. We present an approach to sentence extraction that maps sentences to nodes of a hierarchical ontology. By considering ontology attributes we are able to improve the semantic representation of a sentence's information content. The classifier that maps sentences to the taxonomy is trained using search engines and is therefore very flexible and not bound to a specific domain. In our experiments, we train an SVM classifier to identify summary sentences using ontology-based sentence features. Our experimental results show that the ontology-based extraction of sentences outperforms baseline classifiers, leading to higher Rouge scores of summary extracts.

@INPROCEEDINGS{hennig08b,
title={An Ontology-Based Approach to Text Summarization},
author={Hennig, L. and Umbrath, W. and Wetzker, R.},
booktitle={Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on},
year={2008},
month={Dec.},
volume={3},
number={},
pages={291-294},
abstract={Extractive text summarization aims to create a condensed version of one or more source documents by selecting the most informative sentences. Research in text summarization has therefore often focused on measures of the usefulness of sentences for a summary. We present an approach to sentence extraction that maps sentences to nodes of a hierarchical ontology. By considering ontology attributes we are able to improve the semantic representation of a sentence's information content. The classifier that maps sentences to the taxonomy is trained using search engines and is therefore very flexible and not bound to a specific domain. In our experiments, we train an SVM classifier to identify summary sentences using ontology-based sentence features. Our experimental results show that the ontology-based extraction of sentences outperforms baseline classifiers, leading to higher Rouge scores of summary extracts.},
keywords={feature extraction, ontologies (artificial intelligence), pattern classification, search engines, support vector machines, text analysisSVM classifier, extractive text summarization, hierarchical ontology, search engines, semantic representation},
doi={10.1109/WIIAT.2008.175},
ISSN={}, }
Autoren:
Leonhard Hennig, Robert Wetzker, Winfried Umbrath
Kategorie:
Tagungsbeitrag
Jahr:
2008
Ort:
IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2008), Workshop on Natural Language Processing and Ontology Engineering (NLPOE 2008)