Nam, Jinseok (2014)
Semi-Supervised Neural Networks for Nested Named Entity Recognition.
Workshop on GermEval 2014 Named Entity Recognition Shared Task, KONVENS.
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (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.
Typ des Eintrags: | Konferenzveröffentlichung |
---|---|
Erschienen: | 2014 |
Autor(en): | Nam, Jinseok |
Art des Eintrags: | Bibliographie |
Titel: | Semi-Supervised Neural Networks for Nested Named Entity Recognition |
Sprache: | Englisch |
Publikationsjahr: | 2014 |
Veranstaltungstitel: | Workshop on GermEval 2014 Named Entity Recognition Shared Task, KONVENS |
URL / URN: | http://opus.bsz-bw.de/ubhi/volltexte/2014/308/pdf/03_09.pdf |
Kurzbeschreibung (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. |
Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Knowledge Engineering |
Hinterlegungsdatum: | 25 Nov 2015 08:48 |
Letzte Änderung: | 25 Nov 2015 08:48 |
PPN: | |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
Frage zum Eintrag |
Optionen (nur für Redakteure)
Redaktionelle Details anzeigen |