Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study

Abstract

Named Entity Recognition seeks to extract substrings within a text that name real-world objects and to determine their type (for example, whether they refer to persons or organizations). In this survey, we first present an overview of recent popular approaches, including advancements in Transformer-based methods and Large Language Models (LLMs) that have not had much coverage in other surveys. In addition, we discuss reinforcement learning and graph-based approaches, highlighting their role in enhancing NER performance. Second, we focus on methods designed for datasets with scarce annotations. Third, we evaluate the performance of the main NER implementations on a variety of datasets with differing characteristics (as regards their domain, their size, and their number of classes). We thus provide a deep comparison of algorithms that have never been considered together. Our experiments shed some light on how the characteristics of datasets affect the behavior of the methods we compare.

42 pages

References in corpus (26)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
• Prototypical Networks for Few-shot Learning
• LLaMA: Open and Efficient Foundation Language Models
• NLTK: The Natural Language Toolkit
• Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
• A Survey on Deep Learning for Named Entity Recognition
• Evaluating Large Language Models Trained on Code
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Publicly Available Clinical BERT Embeddings
• Transfer learning for time series classification
• TENER: Adapting Transformer Encoder for Named Entity Recognition
• Few-shot classification in Named Entity Recognition Task
• How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
• GPT-NER: Named Entity Recognition via Large Language Models
• Transfer Learning for Named-Entity Recognition with Neural Networks
• Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering
• T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition
• Few-shot Learning for Named Entity Recognition in Medical Text
• Few-Shot Named Entity Recognition: A Comprehensive Study
• TabLLM: Few-shot Classification of Tabular Data with Large Language Models
• Leveraging Large Language Models for Multiple Choice Question Answering
• NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
• PromptNER: Prompting For Named Entity Recognition
• Transformer-Based Named Entity Recognition for French Using Adversarial Adaptation to Similar Domain Corpora
• Zero-Shot Learning in Named-Entity Recognition with External Knowledge