Dynamic Named Entity Recognition

TL;DR

This paper introduces Dynamic Named Entity Recognition (DNER), a new task emphasizing context-aware entity extraction, and provides benchmarks to evaluate models' ability to utilize context effectively.

Contribution

The paper proposes the DNER task and benchmark datasets, highlighting the importance of context in entity recognition beyond simple classification.

Findings

Baseline models show limited use of context in entity recognition.

DNER datasets reveal challenges in context-dependent entity extraction.

Experiments suggest new research directions for context-aware NER.

Abstract

Named Entity Recognition (NER) is a challenging and widely studied task that involves detecting and typing entities in text. So far,NER still approaches entity typing as a task of classification into universal classes (e.g. date, person, or location). Recent advances innatural language processing focus on architectures of increasing complexity that may lead to overfitting and memorization, and thus, underuse of context. Our work targets situations where the type of entities depends on the context and cannot be solved solely by memorization. We hence introduce a new task: Dynamic Named Entity Recognition (DNER), providing a framework to better evaluate the ability of algorithms to extract entities by exploiting the context. The DNER benchmark is based on two datasets, DNER-RotoWire and DNER-IMDb. We evaluate baseline models and present experiments reflecting issues and research axes related to this novel task.