Year: 2024
Type: article
Abstract: Generally speaking, Named Entity Recognition is one of the major tasks in NLP that involves the identification and classification of named entities mentioned in text, which include, among others, names of people, organizations, locations, dates, etc. This paper analyzes methodologies, models, and advances on NER by exploring traditional approaches and state-of-the-art deep learning techniques. It describes the transition from rule-based systems to machine learning approaches, including current algorithms such as CRFs and HMMs. It discusses the deep learning innovations in recent times: RNNs, LSTMs, and Transformer-based architectures like BERT and RoBERTa. It then analyses key challenges of NER, such as entity ambiguity, domain adaptability, and multilingual processing, together with approaches toward model accuracy improvement and generalizability. The analysis below also discusses pragmatic use cases within domains like information retrieval, customer service, and healthcare and discusses reasons why NER bears importance for improving human-computer interaction.
Author: Swetha Sistla
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4405002891