Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nemoto, Sota, Kitada, Shunsuke, Iyatomi, Hitoshi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913655055974400
author Nemoto, Sota
Kitada, Shunsuke
Iyatomi, Hitoshi
author_facet Nemoto, Sota
Kitada, Shunsuke
Iyatomi, Hitoshi
contents Data imbalance presents a significant challenge in various machine learning (ML) tasks, particularly named entity recognition (NER) within natural language processing (NLP). NER exhibits a data imbalance with a long-tail distribution, featuring numerous minority classes (i.e., entity classes) and a single majority class (i.e., O-class). This imbalance leads to misclassifications of the entity classes as the O-class. To tackle this issue, we propose a simple and effective learning method named majority or minority (MoM) learning. MoM learning incorporates the loss computed only for samples whose ground truth is the majority class into the loss of the conventional ML model. Evaluation experiments on four NER datasets (Japanese and English) showed that MoM learning improves prediction performance of the minority classes without sacrificing the performance of the majority class and is more effective than widely known and state-of-the-art methods. We also evaluated MoM learning using frameworks as sequential labeling and machine reading comprehension, which are commonly used in NER. Furthermore, MoM learning has achieved consistent performance improvements regardless of language or framework.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
Nemoto, Sota
Kitada, Shunsuke
Iyatomi, Hitoshi
Computation and Language
Data imbalance presents a significant challenge in various machine learning (ML) tasks, particularly named entity recognition (NER) within natural language processing (NLP). NER exhibits a data imbalance with a long-tail distribution, featuring numerous minority classes (i.e., entity classes) and a single majority class (i.e., O-class). This imbalance leads to misclassifications of the entity classes as the O-class. To tackle this issue, we propose a simple and effective learning method named majority or minority (MoM) learning. MoM learning incorporates the loss computed only for samples whose ground truth is the majority class into the loss of the conventional ML model. Evaluation experiments on four NER datasets (Japanese and English) showed that MoM learning improves prediction performance of the minority classes without sacrificing the performance of the majority class and is more effective than widely known and state-of-the-art methods. We also evaluated MoM learning using frameworks as sequential labeling and machine reading comprehension, which are commonly used in NER. Furthermore, MoM learning has achieved consistent performance improvements regardless of language or framework.
title Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition
topic Computation and Language
url https://arxiv.org/abs/2401.11431