Global Span Selection for Named Entity Recognition
Urchade Zaratiana, Niama Elkhbir, Pierre Holat, Nadi Tomeh, Thierry Charnois
Abstract
Named Entity Recognition (NER) is an important task in Natural Language Processing with applications in many domains. In this paper, we describe a novel approach to named entity recognition, in which we output a set of spans (i.e., segmentations) by maximizing a global score. During training, we optimize our model by maximizing the probability of the gold segmentation. During inference, we use dynamic programming to select the best segmentation under a linear time complexity. We prove that our approach outperforms CRF and semi-CRF models for Named Entity Recognition. We will make our code publicly available.
Topics & Concepts
Named-entity recognitionComputer scienceInferenceSegmentationArtificial intelligenceTask (project management)Sequence labelingSelection (genetic algorithm)Natural language processingSet (abstract data type)Machine learningDomain (mathematical analysis)Conditional random fieldNamed entityPattern recognition (psychology)Programming languageMathematicsMathematical analysisManagementEconomicsTopic ModelingNatural Language Processing TechniquesText and Document Classification Technologies