TU Darmstadt / ULB / TUbiblio

Semi-Supervised Neural Networks for Nested Named Entity Recognition

Nam, Jinseok (2014):
Semi-Supervised Neural Networks for Nested Named Entity Recognition.
In: Workshop on GermEval 2014 Named Entity Recognition Shared Task, KONVENS, [Online-Edition: http://opus.bsz-bw.de/ubhi/volltexte/2014/308/pdf/03_09.pdf],
[Conference or Workshop Item]

Abstract

In this paper, we investigate a semi-supervised learning approach based on neural networks for nested named entity recognition on the GermEval 2014 dataset. The dataset consists of triples of a word, a named entity associated with that word in the first-level and one in the second-level. Additionally, the tag distribution is highly skewed, that is, the number of occurrences of certain types of tags is too small. Hence, we present a unified neural network architecture to deal with named entities in both levels simultaneously and to improve generalization performance on the classes that have a small number of labelled examples.

Item Type: Conference or Workshop Item
Erschienen: 2014
Creators: Nam, Jinseok
Title: Semi-Supervised Neural Networks for Nested Named Entity Recognition
Language: English
Abstract:

In this paper, we investigate a semi-supervised learning approach based on neural networks for nested named entity recognition on the GermEval 2014 dataset. The dataset consists of triples of a word, a named entity associated with that word in the first-level and one in the second-level. Additionally, the tag distribution is highly skewed, that is, the number of occurrences of certain types of tags is too small. Hence, we present a unified neural network architecture to deal with named entities in both levels simultaneously and to improve generalization performance on the classes that have a small number of labelled examples.

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Knowl­edge En­gi­neer­ing
Event Title: Workshop on GermEval 2014 Named Entity Recognition Shared Task, KONVENS
Date Deposited: 25 Nov 2015 08:48
Official URL: http://opus.bsz-bw.de/ubhi/volltexte/2014/308/pdf/03_09.pdf
Export:

Optionen (nur für Redakteure)

View Item View Item