Task 2: Biomedical question answering over interlinked data

Full description: qald-4.pdf (Last updated: April 1, 2014)

Datasets

• SIDER, describing drugs and their sideffects
• Diseasome, encompassing description of diseases and genetic disorders
• Drugbank, describing FDA-approved active compounds of medication

SPARQL endpoint

We do not maintain a SPARQL endpoint once the challenge is finished. Please load the data into a local triple store.

Training data

The training data comprises 25 English questions over the above datasets, annotated with corresponding SPARQL queries and the answers that these queries retrieve. Many of the questions require the integration of information from at least two datasets.

• qald-4_biomedical_train.xml
• qald-4_biomedical_train_withanswers.xml

Test data

• qald-4_biomedical_test_questions.xml
• qald-4_biomedical_test.xml (with SPARQL queries)
• qald-4_biomedical_test_withanswers.xml (with SPARQL queries and answers)

Evaluation results: qald-4_results.pdf