Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting

Abstract

We discuss ongoing work into automating a multilingual digital helpdesk service available via text messaging to pregnant and breastfeeding mothers in South Africa. Our anonymized dataset consists of short informal questions, often in low-resource languages, with unreliable language labels, spelling errors and code-mixing, as well as template answers with some inconsistencies. We explore cross-lingual word embeddings, and train parametric and non-parametric models on 90K samples for answer selection from a set of 126 templates. Preliminary results indicate that LSTMs trained end-to-end perform best, with a test accuracy of 62.13% and a recall@5 of 89.56%, and demonstrate that we can accelerate response time by several orders of magnitude.