Adapting word2vec to Named Entity Recognition

Objekt

Titel

Adapting word2vec to Named Entity Recognition

Urheber

Scharolta Katharina Sienčnik

Zusammenfassung

In this paper we explore how word vectors built using word2vec can be used to improve the performance of a classifier during Named Entity Recognition. Thereby, we discuss the best integration of word embeddings into the classification problem and consider the effect of the size of the unlabelled dataset on performance, reaching the unexpected result that for this particular task increasing the amount of unlabelled data does not necessarily increase the performance of the classifier.

Datum

2015

Is Part Of

Adapting word2vec to Named Entity Recognition

presented at

Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015, May 11-13, 2015, Vilnius, Lithuania

Verleger

Link�ping University Electronic Press, Link�pings universitet

Seiten

239-243

isbn

1650-3740

Sammlungen