Question Answering


Question Answering (QA) is an application of Information Retrieval (IR) and Natural Language Processing (NLP). Combining techniques from IR and NLP, systems are built to automatically answer questions posed by humans in a natural language. These systems are called QA systems. Their main goal is to retrieve actual answers to questions rather than a ranked list of documents, as most information retrieval systems do. Furthermore, a QA system is a very significant entry point for achieving the communication between humans and machines. Although, QA research dates back to the 1960s, most research has begun in 1999 with the establishment of TREC (Text REtrieval Conference). Nowadays, we observe that the problems defined in QA have not been overcome.  

Our contribution

In our research, we develop QA systems dealing with a wide range of question types including: factoid, list, definition and polar. Our objectives:

  • More intelligent QA systems (understandable answers, deep understanding in questions)
  • Closed-domain QA systems (especially biomedical domain)
  • Useful research tools
  • Efficient utilization of existing knowledge bases (e.g. Semantic MEDLINE DATABASE) and creation of new ones in the context of QA systems
  • Extraction of triples from questions using Open Information Extraction techniques and other semantic tools.


Our systems have been tested at the BioASQ challenge and have won awards.

  • BioASQ 2014
    • Task 2b, Phase B: Extracting Exact Answers
      • 2nd place in batch 4
      • 2nd place in batch 5

  • BioASQ 2016
    • Task 4b, Phase A: Identifying Relevant Concepts
      • 1st place in batches 1, 4 and 5
      • 2nd place in batch 2
    • Task 4b, Phase B: Extracting Exact Answers
      • 1st place in batch 1
      • 2nd place in batch 2     

  • BioASQ 2018
    • Task 6b, Phase B: Extracting Exact Answers
      • 1st place in batch 1, 3 and 4
      • 2nd place in batch 2             


I. Papanikolaou, D. Dimitriadis, G. Tsoumakas, M. Laliotis, N. Markantonatos, I. Vlahavas, “Ensemble Approaches for Large-Scale Multi-Label Classification and Question Answering in Biomedicine”, Proceedings BioASQ 2014 Workshop, Sheffield, UK, 2014.

E. Papagiannopoulou, Y. Papanikolaou, D. Dimitriadis, S. Lagopoulos, G. Tsoumakas, M. Laliotis, N. Markantonatos, I. Vlahavas (2016) "Large-Scale Semantic Indexing and Question Answering in Biomedicine", In Proceedings of the BioASQ 2016 Workshop.