Skip to content

Latest commit

 

History

History
13 lines (9 loc) · 853 Bytes

README.md

File metadata and controls

13 lines (9 loc) · 853 Bytes

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].

Specification

  • 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.