Question-aware Transformer Models for Consumer Health Question Summarization

TL;DR

This paper introduces a question-aware transformer model for abstractive summarization of consumer health questions, improving understanding and relevance of summaries by recognizing medical entities and question types, leading to better question answering performance.

Contribution

The paper proposes a novel transformer-based model that incorporates medical entity recognition and question-type information for improved health question summarization.

Findings

Outperformed state-of-the-art by 10.2 ROUGE-L points on MeQSum.

Effective in capturing key medical entities for better summaries.

Manual evaluation confirmed improved correctness of summaries.

Abstract

Searching for health information online is becoming customary for more and more consumers every day, which makes the need for efficient and reliable question answering systems more pressing. An important contributor to the success rates of these systems is their ability to fully understand the consumers' questions. However, these questions are frequently longer than needed and mention peripheral information that is not useful in finding relevant answers. Question summarization is one of the potential solutions to simplifying long and complex consumer questions before attempting to find an answer. In this paper, we study the task of abstractive summarization for real-world consumer health questions. We develop an abstractive question summarization model that leverages the semantic interpretation of a question via recognition of medical entities, which enables the generation of informative summaries. Towards this, we propose multiple Cloze tasks (i.e. the task of filing missing words in a given context) to identify the key medical entities that enforce the model to have better coverage in question-focus recognition. Additionally, we infuse the decoder inputs with question-type information to generate question-type driven summaries. When evaluated on the MeQSum benchmark corpus, our framework outperformed the state-of-the-art method by 10.2 ROUGE-L points. We also conducted a manual evaluation to assess the correctness of the generated summaries.