Cross-document attention-based gated fusion network for automated medical licensing exam

Jiandong Liu, Jianfeng Ren, Zheng Lu, Wentao He, Menglin Cui, Zibo Zhang, Ruibin Bai

Research output: Journal PublicationArticlepeer-review

3 Citations (Scopus)

Abstract

One of the applications of machine-learning in the medical industry is to automatically learn knowledge from medical textbooks and transfer medical knowledge into diagnosis abilities. Because of complex nature of medical issues, the learning process usually requires multiple knowledge documents to form a comprehensive reasoning chain for diagnosis, which increases the difficulty of the automatic learning process. Existing models for multiple document comprehension either concatenate multiple documents together for inference or reason on every document independently. In this paper, we propose a Co-Attention-based Multi-document Inference (CAMI) framework for better reasoning over multiple documents. The proposed framework makes use of not only the attentional information among questions, answers and support documents but also the complementary attentional information across different documents. In addition, a gated fusion network is designed to fuse the cross-document information. The proposed model outperforms the state-of-the-art methods on Chinese National Medical Licensing Examination (CNMLE) dataset, ClinicQA, which contains 27,432 plain text documents and 13,827 CNMLE questions. We intend to make it publicly available as the first clinical OpenQA dataset.

Original languageEnglish
Article number117588
JournalExpert Systems with Applications
Volume205
DOIs
Publication statusPublished - 1 Nov 2022

Keywords

  • Clinical diagnosis
  • Machine reading comprehension
  • Multiple document reasoning

ASJC Scopus subject areas

  • General Engineering
  • Computer Science Applications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Cross-document attention-based gated fusion network for automated medical licensing exam'. Together they form a unique fingerprint.

Cite this