only search NEJLT

Volume 5, Article 1, 2018

Part of Speech Tagging: Shallow or Deep Learning?

Author: Robert Östling*
Affiliation: *Department of Linguistics, Stockholm University
DOI: 10.3384/nejlt.2000-1533.1851
Volume: 5
Article No.: 1
Available: 2018-06-19
View Article: Pdf fileView Article (PDF); References (HTML)
No. of pages: 15
Pages: 1-5
Abstract: Deep neural networks have advanced the state of the art in numerous fields, but they generally suffer from low computational efficiency and the level of improvement compared to more efficient machine learning models is not always significant. We perform a thorough PoS tagging evaluation on the Universal Dependencies treebanks, pitting a state-of-the-art neural network approach against UDPipe and our sparse structured perceptron-based tagger, efselab. In terms of computational efficiency, efselab is three orders of magnitude faster than the neural network model, while being more accurate than either of the other systems on 47 of 65 treebanks.

Publishing host : Linköping University Electronic Press, Linköpings universitet