Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction

Chen Lin, Timothy Miller, Dmitriy Dligach, Hadi Amiri, Steven Bethard, Guergana Savova


Abstract
Neural network models are oftentimes restricted by limited labeled instances and resort to advanced architectures and features for cutting edge performance. We propose to build a recurrent neural network with multiple semantically heterogeneous embeddings within a self-training framework. Our framework makes use of labeled, unlabeled, and social media data, operates on basic features, and is scalable and generalizable. With this method, we establish the state-of-the-art result for both in- and cross-domain for a clinical temporal relation extraction task.
Anthology ID:
W18-5619
Volume:
Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Venues:
EMNLP | Louhi | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
165–176
Language:
URL:
https://aclanthology.org/W18-5619
DOI:
10.18653/v1/W18-5619
Bibkey:
Cite (ACL):
Chen Lin, Timothy Miller, Dmitriy Dligach, Hadi Amiri, Steven Bethard, and Guergana Savova. 2018. Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction. In Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis, pages 165–176, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction (Lin et al., 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5619.pdf
Data
MIMIC-III