preprintJan 1, 2020GOLD OA

A Unified MRC Framework for Named Entity Recognition

Shannon Applied Biotechnology Centre · Zhejiang University

Indexed incrossref

Abstract

The task of named entity recognition (NER) is normally divided into nested NER and flat NER depending on whether named entities are nested or not. Models are usually separately developed for the two tasks, since sequence labeling models are only able to assign a single label to a particular token, which is unsuitable for nested NER where a token may be assigned several labels.

Citation impact

620
total citations
FWCI
61.74
Percentile
100%
References
63
Citations per year

Authors

6

Topics & keywords

Keywords
  • Named-entity recognition
  • Computer science
  • Task (project management)
  • Question answering
  • Entity linking
  • Artificial intelligence
  • Natural language processing
  • Security token
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.

Funding