Jeremy Barnes
Department of Informatics, University of Oslo, Norway
Samia Touileb
Department of Informatics, University of Oslo, Norway
Lilja Øvrelid
Department of Informatics, University of Oslo, Norway
Erik Velldal
Department of Informatics, University of Oslo, Norway
Download articlePublished in: Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland
Linköping Electronic Conference Proceedings 167:19, p. 175--186
NEALT Proceedings Series 42:19, p. 175--186
Published: 2019-10-02
ISBN: 978-91-7929-995-8
ISSN: 1650-3686 (print), 1650-3740 (online)
This paper explores the use of multi-task learning (MTL) for incorporating external knowledge in neural models. Specifically, we show how MTL can enable a BiLSTM sentiment classifier to incorporate information from sentiment lexicons. Our MTL set-up is shown to improve model performance (compared to a single-task set-up) on both English and Norwegian sentence-level sentiment datasets. The paper also introduces a new sentiment lexicon for Norwegian.