Dynamic Named Entity Recognition
This work addresses the challenge of context-dependent entity typing in NLP, which is incremental as it builds on existing NER frameworks.
The authors tackled the problem of Named Entity Recognition (NER) by introducing Dynamic Named Entity Recognition (DNER), a new task where entity types depend on context, and provided a benchmark with two datasets (DNER-RotoWire and DNER-IMDb) to evaluate algorithms.
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.