What question did this study set out to answer?

The aim is to improve named entity recognition in Japanese medical documents with limited labeled data.

April 1, 2026Open Access

NTTD at the NTCIR-16 Real-MedNLP Task

Key Points

The aim is to improve named entity recognition in Japanese medical documents with limited labeled data.
Participated in Subtask1-CR-JA and Subtask1-RR-JA of NTCIR-16.
Utilized an annotation inconsistency detection tool to correct training data labels.
Employed data augmentation methods to generate additional labeled data.
Fine-tuned the Flair model using the combined training data.
Achieved improvements in named entity recognition performance.
Successfully integrated original and augmented data for model training.

Abstract

The NTTD team participated in the Subtask1-CR-JA and Subtask1-RR-JA subtasks of the NTCIR-16 Real-MedNLP Task. This paper reports our approach to solving the NER (named entity recognition) problem when dealing with limited labeled medical documents. The documents are real Case-Report and Radiographic-Report data in Japanese. We first applied out recently developed annotation inconsistency detection tool to detect and correct inappropriate labels within the given training data. Then we applied data augmentation methods to create additional labeled data and combined the original and additional data as training data of our model. In this task, we fine-tuned Flair by the forementioned training data and acquired the results.

Read Full Paperexternally

AIに質問

Bookmark

View Full Paper