PoS-tagging and lemmatization with a deep recurrent neural network

Ugray, Gábor: PoS-tagging and lemmatization with a deep recurrent neural network. Magyar Számítógépes Nyelvészeti Konferencia, (13). pp. 215-224. (2019)

[img] Cikk, tanulmány, mű
msznykonf_015_215-224.pdf

Download (428kB)

Abstract

Neural networks have been shown to successfully solve many natural language processing tasks previously tackled by rule-based and statistical approaches. We present a deep recurrent network with long short-term memory, identical to engines used in machine translation, to solve the problem of joint PoS-tagging and lemmatization in Hungarian and German. Our model achieves comparable or superior results to a state-of-the-art statistical PoS tagger. We are able to enhance the Hungarian model’s performance, as measured on a manually annotated sample unrelated to the initial training corpus, through an additional synthesized dataset.

Item Type: Article
Event Title: Magyar Számítógépes Nyelvészeti Konferencia (15.) (2019) (Szeged)
Journal or Publication Title: Magyar Számítógépes Nyelvészeti Konferencia
Date: 2019
Volume: 13
Page Range: pp. 215-224
ISBN: 978-963-315-393-2
Uncontrolled Keywords: Nyelvészet - számítógép alkalmazása
Additional Information: Bibliogr.: p. 223-224. ; összefoglalás angol nyelven
Date Deposited: 2019. Jul. 03. 13:25
Last Modified: 2019. Jul. 03. 13:25
URI: http://acta.bibl.u-szeged.hu/id/eprint/59087

Actions (login required)

View Item View Item