Skip to content

Deep Learning architectures for the fascinating task of sentence selection for QA systems.

Notifications You must be signed in to change notification settings


Folders and files

Last commit message
Last commit date

Latest commit



10 Commits

Repository files navigation

Sentence Selection for QA

This software accompanies the M.Sc. Thesis: "Sentence selection from biomedical documents for question answering".

It also accompanies the following paper:

G. Brokos, P. Liosis, R. McDonald, D. Pappas and I. Androutsopoulos, "AUEB at BioASQ 6: Document and Snippet Retrieval". Proceedings of the workshop BioASQ: Large-scale Biomedical Semantic Indexing and Question Answering, at the Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), Brussels, Belgium, 2018.[PDF].


  • BM25: Implementation of BM25 ranking function.
  • DL_Models: Deep Learning model used.
  • Extract_BioASQ_Data: Extract data from BioASQ's published json files and create datasets with various formats.