Improving Multi-label Emotion Classification via Sentiment Classification with Dual Attention Transfer Network

Jianfei Yu, Luís Marujo, Jing Jiang, Pradeep Karuturi, William Brendel


Abstract
In this paper, we target at improving the performance of multi-label emotion classification with the help of sentiment classification. Specifically, we propose a new transfer learning architecture to divide the sentence representation into two different feature spaces, which are expected to respectively capture the general sentiment words and the other important emotion-specific words via a dual attention mechanism. Experimental results on two benchmark datasets demonstrate the effectiveness of our proposed method.
Anthology ID:
D18-1137
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1097–1102
Language:
URL:
https://aclanthology.org/D18-1137
DOI:
10.18653/v1/D18-1137
Bibkey:
Cite (ACL):
Jianfei Yu, Luís Marujo, Jing Jiang, Pradeep Karuturi, and William Brendel. 2018. Improving Multi-label Emotion Classification via Sentiment Classification with Dual Attention Transfer Network. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1097–1102, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Improving Multi-label Emotion Classification via Sentiment Classification with Dual Attention Transfer Network (Yu et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1137.pdf