YerevaNN

Research topics

• Time series prediction on medical data
  • A set of benchmarks on MIMIC-III dataset [preprint] [code]
  • LSTM-based models for the benchmarks [weights]
  • This is a collaboration with USC ISI. Partially funded by ISTC.
• Natural language processing with deep learning
  • Developing a joint POS tagger, lemmatizer and dependency parser called JointUD [paper] [code]
  • Developing a relation extraction pipeline for biomedical texts [code]
  • Reproducing DIIN network for NLI [report] [code]
  • Reproducing R-NET network for QA [blogpost] [code]
  • This is a collaboration with USC ISI.
• Development of Armenian treebanks
  • Developing Eastern Armenian treebank according to the Universal Dependencies specifications [website] [code]
  • The first version is included in UD v2.2 [data]
  • This is a collaboration with Marat Yavrumyan and Anna Danielyan from Yerevan State University. Partially funded by ANSEF and ISTC.