Topic Detection and Tracking: Event-Based Information Organization
Topic Detection and Tracking: Event-Based Information Organization
Text chunking based on a generalization of winnow
The Journal of Machine Learning Research
Sub-event based multi-document summarization
HLT-NAACL-DUC '03 Proceedings of the HLT-NAACL 03 on Text summarization workshop - Volume 5
Evita: a robust event recognizer for QA systems
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Identification of event mentions and their semantic class
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Effective use of TimeBank for TimeML analysis
Proceedings of the 2005 international conference on Annotating, extracting and reasoning about time and events
TimeML events recognition and classification: learning CRF models with semantic roles
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Data Mining: Practical Machine Learning Tools and Techniques
Data Mining: Practical Machine Learning Tools and Techniques
Hi-index | 0.00 |
The goal of this research is to devise a method for recognizing and classifying TimeML events in a more effective way. TimeML is the most recent annotation scheme for processing the event and temporal expressions in natural language processing fields. In this paper, we argue and demonstrate that unit feature dependency information and deep-level WordNet hypernyms are useful for event recognition and type classification. The proposed method utilizes various features including lexical semantic and dependency-based combined features. The experimental results show that our proposed method outperforms a state-of-the-art approach, mainly due to the new strategies. Especially, the performance of noun and adjective events, which have been largely ignored and yet significant, is significantly improved.