Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks

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


Abstract
Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task.
Anthology ID:
W17-2341
Volume:
BioNLP 2017
Month:
August
Year:
2017
Address:
Vancouver, Canada,
Editors:
Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, Junichi Tsujii
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
322–327
Language:
URL:
https://aclanthology.org/W17-2341
DOI:
10.18653/v1/W17-2341
Bibkey:
Cite (ACL):
Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, and Guergana Savova. 2017. Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks. In BioNLP 2017, pages 322–327, Vancouver, Canada,. Association for Computational Linguistics.
Cite (Informal):
Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks (Lin et al., BioNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-2341.pdf