Joint Learning for Targeted Sentiment Analysis

Dehong Ma, Sujian Li, Houfeng Wang


Abstract
Targeted sentiment analysis (TSA) aims at extracting targets and classifying their sentiment classes. Previous works only exploit word embeddings as features and do not explore more potentials of neural networks when jointly learning the two tasks. In this paper, we carefully design the hierarchical stack bidirectional gated recurrent units (HSBi-GRU) model to learn abstract features for both tasks, and we propose a HSBi-GRU based joint model which allows the target label to have influence on their sentiment label. Experimental results on two datasets show that our joint learning model can outperform other baselines and demonstrate the effectiveness of HSBi-GRU in learning abstract features.
Anthology ID:
D18-1504
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:
4737–4742
Language:
URL:
https://aclanthology.org/D18-1504
DOI:
10.18653/v1/D18-1504
Bibkey:
Cite (ACL):
Dehong Ma, Sujian Li, and Houfeng Wang. 2018. Joint Learning for Targeted Sentiment Analysis. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4737–4742, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Joint Learning for Targeted Sentiment Analysis (Ma et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1504.pdf
Video:
 https://aclanthology.org/D18-1504.mp4