Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification

Jianfei Yu, Jing Jiang


Abstract
In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification. We first design a new auxiliary task based on sentiment scores of domain-independent words. We then propose two neural network architectures to respectively induce document embeddings and sentence embeddings that work well for different domains. When these document and sentence embeddings are used for sentiment classification, we find that with both pseudo and external sentiment lexicons, our proposed methods can perform similarly to or better than several highly competitive domain adaptation methods on a benchmark dataset of product reviews.
Anthology ID:
I17-1066
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
654–663
Language:
URL:
https://aclanthology.org/I17-1066
DOI:
Bibkey:
Cite (ACL):
Jianfei Yu and Jing Jiang. 2017. Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 654–663, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification (Yu & Jiang, IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/I17-1066.pdf