Snowball: extracting relations from large plain-text collections
DL '00 Proceedings of the fifth ACM conference on Digital libraries
Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Automatic acquisition of domain knowledge for Information Extraction
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Counter-training in discovery of semantic patterns
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
A semantic approach to IE pattern induction
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Redundancy-based correction of automatically extracted facts
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Predicting unknown time arguments based on cross-event propagation
ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Bootstrapping events and relations from text
Bootstrapping events and relations from text
Using document level cross-event inference to improve event extraction
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Automatically generating extraction patterns from untagged text
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Filtered ranking for bootstrapping in event extraction
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
| Hi-index | 0.00 |
Annotating training data for event extraction is tedious and labor-intensive. Most current event extraction tasks rely on hundreds of annotated documents, but this is often not enough. In this paper, we present a novel self-training strategy, which uses Information Retrieval (IR) to collect a cluster of related documents as the resource for bootstrapping. Also, based on the particular characteristics of this corpus, global inference is applied to provide more confident and informative data selection. We compare this approach to self-training on a normal newswire corpus and show that IR can provide a better corpus for bootstrapping and that global inference can further improve instance selection. We obtain gains of 1.7% in trigger labeling and 2.3% in role labeling through IR and an additional 1.1% in trigger labeling and 1.3% in role labeling by applying global inference.