Yes/No Question Answering in BioASQ 2019

Abstract

The field of question answering has gained greater attention with the rise of deep neural networks. More and more approaches adopt paradigms which are based primarily on the powerful language representations models and transfer learning techniques to build efficient learning models which are able to outperform current state of the art systems. Endorsing this current trend, in this paper, we strive to take a step towards the goal of answering yes/no questions in the field of biomedicine. Specifically, the task is to give a short answer (yes or no) for a question written in natural language, finding clues including in a set of snippets that are related with this question. We propose three different deep neural network models, which are free of assumptions about predefined specific feature functions, while the key elements of these are the ELMo embeddings, the similarity matrices and/or sentiment information. The results have shown that incorporating the sentiment, we can improve the performance of a yes/no question answering system while the proposed learning models significantly outperform the BioASQ baseline.