KULeuven-LIIR at SemEval-2017 Task 12: Cross-Domain Temporal Information Extraction from Clinical Records
TL
TL;DR
The authors' system performed above average for all subtasks in both phases of Clinical TempEval 2017, using a combination of Support Vector Machines (SVM) for event and temporal expression detection, and a structured perceptron for extracting temporal relations.
Abstract
In this paper, we describe the system of the KULeuven-LIIR submission for Clinical TempEval 2017. We participated in all six subtasks, using a combination of Support Vector Machines (SVM) for event and temporal expression detection, and a structured perceptron for extracting temporal relations. Moreover, we present and analyze the results from our submissions, and verify the effectiveness of several system components. Our system performed above average for all subtasks in both phases.
References11 items
1
SemEval-2017 Task 12: Clinical TempEval
2
Temporal Annotation in the Clinical Domain
3
LIBLINEAR: A Library for Large Linear Classification
4
Instance Weighting for Domain Adaptation in NLP
5