Healx Logo

Healx scientists present two new papers at EMNLP 2019 in Hong Kong

Meet Yannis Papanikolaou at the DeepLo workshop on the 3rd of November and Saatviga Sudhahar at the TextGraphs workshop on the 4th to learn more about their latest publications.
1 November 2019   |  
X minutes
Featured image

Poster #1: Deep Bidirectional Transformers for Relation Extraction without Supervision 

NLP Scientist, Yannis Papanikolaou, will be presenting his work on relationship extraction, using a fine-tuning of Google’s BERT language model. Being able to successfully extract relationships despite scarce data is vital to discovering treatments for rare diseases, for which funds – and therefore research – tends to be limited. 

BERT (Bidirectional Encoder Representations from Transformers) is one of Google’s most advanced language models for NLP. Its key innovation is in the bidirectional training of Transformer, which gives the model a stronger sense of language context and flow. 

 

Poster #2: Reasoning Over Paths via Knowledge Base Completion

Machine Learning Scientist, Saatviga Sudhahar, will discuss her work on developing a knowledge-based model to explain novel connections between biomedical entities. Her method ranks the most relevant paths, given the thousands of connections available.

Saatviga uses a simple compositional method, and frames the problem in a novel way to infer explanations from the knowledge graph where direct information is not known. Once again, this is important in discovering new treatments and we use it internally to assist us in defining our drug discovery hypotheses. 

We hope you see in Hong Kong for EMNLP 2019. If you aren’t able to attend but would like more information about either Yannis or Saatviga’s work, please get in touch with us.

You might also like: