Abstract
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.- Anthology ID:
- W19-6119
- Volume:
- Proceedings of the 22nd Nordic Conference on Computational Linguistics
- Month:
- September–October
- Year:
- 2019
- Address:
- Turku, Finland
- Editors:
- Mareike Hartmann, Barbara Plank
- Venue:
- NoDaLiDa
- SIG:
- Publisher:
- Linköping University Electronic Press
- Note:
- Pages:
- 175–186
- Language:
- URL:
- https://aclanthology.org/W19-6119
- DOI:
- Cite (ACL):
- Jeremy Barnes, Samia Touileb, Lilja Øvrelid, and Erik Velldal. 2019. Lexicon information in neural sentiment analysis: a multi-task learning approach. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 175–186, Turku, Finland. Linköping University Electronic Press.
- Cite (Informal):
- Lexicon information in neural sentiment analysis: a multi-task learning approach (Barnes et al., NoDaLiDa 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W19-6119.pdf
- Code
- ltgoslo/norsentlex + additional community code
- Data
- SST