UW-BHI at MEDIQA 2019: An Analysis of Representation Methods for Medical Natural Language Inference
This work addresses the problem of improving medical NLP tasks for healthcare applications by evaluating knowledge-based augmentations, but it is incremental as it applies existing methods to a specific domain without introducing new techniques.
The paper compared three representation methods (BERT, ESP, Cui2Vec) for medical natural language inference using an ESIM model on the MedNLI dataset, finding that BERT achieved the highest performance with an accuracy of 84.5%, while ESP and Cui2Vec scored 78.2% and 76.8%, respectively.
Recent advances in distributed language modeling have led to large performance increases on a variety of natural language processing (NLP) tasks. However, it is not well understood how these methods may be augmented by knowledge-based approaches. This paper compares the performance and internal representation of an Enhanced Sequential Inference Model (ESIM) between three experimental conditions based on the representation method: Bidirectional Encoder Representations from Transformers (BERT), Embeddings of Semantic Predications (ESP), or Cui2Vec. The methods were evaluated on the Medical Natural Language Inference (MedNLI) subtask of the MEDIQA 2019 shared task. This task relied heavily on semantic understanding and thus served as a suitable evaluation set for the comparison of these representation methods.