CORDER: COmmunity relation discovery by named entity recognition
Proceedings of the 3rd international conference on Knowledge capture
A state of the art of Thai Language resources and Thai Language behavior analysis and modeling
COLING '02 Proceedings of the 3rd workshop on Asian language resources and international standardization - Volume 12
Discovering relations among named entities from large corpora
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Clustering for unsupervised relation identification
Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
Simultaneous character-cluster-based word segmentation and named entity recognition in Thai language
KICSS'10 Proceedings of the 5th international conference on Knowledge, information, and creativity support systems
Hi-index | 0.00 |
Relation extraction among named entities is one of the most important tasks in information extraction. This paper presents a feature-based approach for extracting relations among named entities from Thai news documents. In this approach, shallow linguistic processing, including pattern-based named entity extraction, is performed to construct several sets of features. Four supervised learning schemes are applied alternatively to investigate the performance of relation extraction using different feature sets. Focusing on four different types of relations in crime-related news documents, the experimental result shows that the proposed method achieves up to an accuracy of 95% using a data set of 1736 entity pairs. Effect of each set of features on relation extraction is explored for further discussion.