Contrasting Rule-based and Support Vector Machine Approaches to Time Expression Identification in Clinical TempEval
Abstract
We present two approaches to time expression identification, as entered in to SemEval2015 Task 6, Clinical TempEval. The first is a comprehensive rule-based approach that favoured recall, and which achieved the best recall for time expression identification in Clinical TempEval. The second is an SVM-based system built using readily available components, which was able to achieve a competitive F1 in a short development time. We discuss how the two approaches perform relative to each other, and how characteristics of the corpus affect the suitability of different approaches and their outcomes.
URL
http://www.aclweb.org/anthology/S15-2141
DOI
10.18653/v1/S15-2141
LaTeX
@inproceedings{Tissot2015SemEval,
author = {Tissot, Hegler and Gorrell, Genevieve and Roberts, Angus and Derczynski, Leon and Fabro, Marcos Didonet Del},
title = {{UFPRSheffield}: Contrasting Rule-based and Support Vector Machine Approaches to Time Expression Identification in Clinical TempEval},
booktitle = {Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)},
month = {June},
year = {2015},
address = {Denver, Colorado},
publisher = {Association for Computational Linguistics},
pages = {835--839},
url = {http://www.aclweb.org/anthology/S15-2141}
}