Composited-Nested-Learning with Data Augmentation for Nested Named Entity Recognition

TL;DR

This paper introduces a novel data augmentation method called Composited-Nested-Learning with Confidence Filtering Mechanism for Nested Named Entity Recognition, improving performance on ACE datasets by addressing data scarcity and class imbalance.

Contribution

It proposes a new data augmentation framework using Composited-Nested-Label Classification and Confidence Filtering Mechanism tailored for NNER tasks, which was not explored before.

Findings

Improves NNER performance on ACE2004 and ACE2005 datasets.

Alleviates sample imbalance issues in nested entity recognition.

Demonstrates effectiveness of composited-nested structures for data augmentation.

Abstract

Nested Named Entity Recognition (NNER) focuses on addressing overlapped entity recognition. Compared to Flat Named Entity Recognition (FNER), annotated resources are scarce in the corpus for NNER. Data augmentation is an effective approach to address the insufficient annotated corpus. However, there is a significant lack of exploration in data augmentation methods for NNER. Due to the presence of nested entities in NNER, existing data augmentation methods cannot be directly applied to NNER tasks. Therefore, in this work, we focus on data augmentation for NNER and resort to more expressive structures, Composited-Nested-Label Classification (CNLC) in which constituents are combined by nested-word and nested-label, to model nested entities. The dataset is augmented using the Composited-Nested-Learning (CNL). In addition, we propose the Confidence Filtering Mechanism (CFM) for a more efficient selection of generated data. Experimental results demonstrate that this approach results in improvements in ACE2004 and ACE2005 and alleviates the impact of sample imbalance.