A Unified MRC Framework for Named Entity Recognition
Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, Jiwei Li
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.
Topics & Concepts
Named-entity recognitionComputer scienceTask (project management)Question answeringEntity linkingArtificial intelligenceNatural language processingSecurity tokenSequence (biology)Process (computing)Sequence labelingProgramming languageKnowledge baseManagementGeneticsComputer securityEconomicsBiologyTopic ModelingNatural Language Processing TechniquesService-Oriented Architecture and Web Services