Conference Proceeding Article
In this paper, we study domain adaptationwith a state-of-the-art hierarchicalneural network for document-level sentimentclassification. We first design a newauxiliary task based on sentiment scoresof domain-independent words. We thenpropose two neural network architecturesto respectively induce document embeddingsand sentence embeddings that workwell for different domains. When thesedocument and sentence embeddings areused for sentiment classification, we findthat with both pseudo and external sentimentlexicons, our proposed methods canperform similarly to or better than severalhighly competitive domain adaptationmethods on a benchmark dataset of productreviews.
Databases and Information Systems | Numerical Analysis and Scientific Computing
Data Science and Engineering
Proceedings of the 8th International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017 November 27 - December 1
City or Country
YU, Jianfei and JIANG, Jing.
Leveraging auxiliary tasks for document-level cross-domain sentiment classification. (2017). Proceedings of the 8th International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017 November 27 - December 1. 654-663. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3902
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.