Learning sentence embeddings with auxiliary tasks for cross-domain sentiment classification

• Main Authors: YU, Jianfei, JIANG, Jing
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2016
• Subjects: Benchmark datasets; Cross-domain; Joint modeling; Sentiment classification; State-of-the-art methods; Databases and Information Systems; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/3437; https://ink.library.smu.edu.sg/context/sis_research/article/4438/viewcontent/emnlp2016__2_.pdf
• Institution: Singapore Management University

In this paper, we study cross-domain sentiment classification with neural network architectures. We borrow the idea from Structural Correspondence Learning and use two auxiliary tasks to help induce a sentence embedding that supposedly works well across domains for sentiment classification. We also propose to jointly learn this sentence embedding together with the sentiment classifier itself. Experiment results demonstrate that our proposed joint model outperforms several state-of-the-art methods on five benchmark datasets.