What question did this study set out to answer?

This research aims to enhance medical text processing using advanced language models under limited training resources.

April 1, 2026Open Access

FRDC at the NTCIR-16 Real-MedNLP Task

Key Points

This research aims to enhance medical text processing using advanced language models under limited training resources.
Participated in three sub-tasks: Subtask1-CR-EN, Subtask3-CR-EN (ADE), Subtask3-RR-EN (CI).
Utilized pre-trained language models like BERT and BioBERT for learning representations.
Employed various networks designed around PTLMs tailored for each sub-task.
Adopted effective strategies such as data augmentation to improve model performance.
Achieved the highest score in the CI sub-task.
Ranked 2nd in the ADE sub-task during the official run.

Abstract

In this paper, we describe the approaches of FRDC team for the Real-MedNLP task. Specially, the FRDC team participated in three sub-tasks including Subtask1-CR-EN, Subtask3-CR-EN (ADE), and Subtask3-RR-EN (CI). The Real-MedNLP task aims to promote approaches for supporting real medical services under constrained training resources. We applied pre-trained language models (PTLMs) such as BERT and BioBERT to learn sentence and document representations. For each sub-task, we designed different networks based on PTLMs. Various effective methods such data augmentation were adopted in each sub-task. In the official run, we achieved the best score for the CI sub-task, and ranked 2nd in the ADE sub-task.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper