Pentagon at MEDIQA 2019: Multi-task Learning for Filtering and Re-ranking Answers using Language Inference and Question Entailment

TL;DR

This paper presents a multi-task learning system using pre-trained language models to improve answer filtering and re-ranking in medical question answering, achieving state-of-the-art results on a shared task.

Contribution

The work introduces an end-to-end multi-task system leveraging domain-specific pre-trained models for answer filtering and re-ranking in medical QA tasks.

Findings

Achieved highest Spearman's Rho of 0.338

Achieved Mean Reciprocal Rank of 0.9622

Demonstrated effectiveness of multi-task learning in medical QA

Abstract

Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin. More recently, pre-trained models from large related datasets have been able to perform well on many downstream tasks by just fine-tuning on domain-specific datasets . However, using powerful models on non-trivial tasks, such as ranking and large document classification, still remains a challenge due to input size limitations of parallel architecture and extremely small datasets (insufficient for fine-tuning). In this work, we introduce an end-to-end system, trained in a multi-task setting, to filter and re-rank answers in the medical domain. We use task-specific pre-trained models as deep feature extractors. Our model achieves the highest Spearman's Rho and Mean Reciprocal Rank of 0.338 and 0.9622 respectively, on the ACL-BioNLP workshop MediQA Question Answering shared-task.