Conference Proceeding Article
In this paper, we study cross-domain sentimentclassification with neural network architectures.We borrow the idea from StructuralCorrespondence Learning and use two auxiliarytasks to help induce a sentence embeddingthat supposedly works well across domains forsentiment classification. We also propose tojointly learn this sentence embedding togetherwith the sentiment classifier itself. Experimentresults demonstrate that our proposedjoint model outperforms several state-of-the artmethods on five benchmark datasets.
Databases and Information Systems | Software Engineering
Data Management and Analytics
EMNLP 2016: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing: Austin, Texas, 2016 November 1-25
Association for Computational Linguistics
City or Country
YU, Jianfei and JIANG, Jing.
Learning sentence embeddings with auxiliary tasks for cross-domain sentiment classification. (2016). EMNLP 2016: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing: Austin, Texas, 2016 November 1-25. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3437
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.