SemEval-2013 Task 9: Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013)
1. SemEval-2013: International Workshop on Semantic Evaluation
June 14-15, Atlanta, Georgia
SemEval-2013 Task 9: Extraction of Drug-Drug Interactions
from Biomedical Texts (DDIExtraction 2013)
Isabel Segura-Bedmar, Paloma Martínez, María Herrero-Zazo,
Computer Science Department, Universidad Carlos III de Madrid, Spain
{isegura, pmf, mhzazo}@inf.uc3m.es
Motivation:
A drug-drug interaction (DDI) occurs when one drug influences the level or activity of another drug. Drug Interaction databases are rarely
complete => Medical literature is the most effective source for the detection of drug interactions.
The goal of this shared task is to promote research on Information Extraction techniques applied to the pharmacovigilance domain.
ACKNOWLEDGMENTS:
This work was supported by the Regional Government of Madrid under the Research Network MA2VICMR [S2009/TIC-1542] and by the
Spanish Ministry of Education under the project MULTIMEDICA [TIN2010-20644-C03-01]. We would like to thank all participants for their
efforts and to congratulate them to their interesting work.
We thank the team at the Humboldt-Universitaet zu Berlin for making available a visualization of the DDI corpus using Stav:
http://http://corpora.informatik.hu-berlin.de/, https://github.com/TsujiiLaboratory/stav
Task 9.1. Recognition and Classification of
pharmacological substances
Task 9.1 Results
Task 9.2 Results
F1 F1
F1
F1
F1
F1
F1
F1
Test dataset: 54 DrugBank documents + 58 MedLine abstracts.
Gold standard annotations of pharmacological substances are provided to teams
both for training and test datasets.
Test dataset: 158 DrugBank documents + 33 MedLine abstracts.
Gold annotations entities were provided
Task 9.2. Extraction and Classification of drug-drug
interactions
Team Affiliation Approach
LASIGE University of Lisbon Conditional Random Fields
UEM_UC3M European University of Madrid, University Carlos
III of Madrid
Ontology-based approach
UMCC_DLSI Matanzas University, University of Alicante J48 classifier
Uturku University of Turku, Finland SVM classifier (TEES system)
WBI_NER Humboldt University of Berlin Conditional Random Fields Team Affiliation Approach
FBK-irst FBK-irst Hybrid kernel + scope of negations and semantic
roles
NIL_UCM University Complutense of Madrid SVM classifier
SCAI Fraunhofer SCAI SVM classifier
UC3M University Carlos III of Madrid Shallow Linguistic Kernel
UCOLORADO_SOM University of Colorado SMV classifier
Uturku University of Turku SVM classifier (TEES system)
UWM_TRIADS University of Wisconsin Two-stage SVM
WBI_DDI Humboldt University of Berlin Ensemble of kernels + TEES system + Moara system