Journal article
Cross-lingual sentiment classification with stacked autoencoders
Knowledge and information systems, v 47(1)
01 Apr 2016
Abstract
Cross-lingual sentiment classification is a popular research topic in natural language processing. The fundamental challenge of cross-lingual learning stems from a lack of overlap between the feature spaces of the source language data and the target language data. In this article, we propose a new model which uses stacked autoencoders to learn language-independent high-level feature representations for the both languages in an unsupervised fashion. The proposed framework aims to force the aligned input bilingual sentences into a common latent space, and the objective function is defined by minimizing the input and output vector representations as well as the distance of the common representations in the latent space. Sentiment classifiers trained on the source language can be adapted to predict sentiment polarity of the target language with the language-independent high-level feature representations. We conduct extensive experiments on English-Chinese sentiment classification tasks of multiple data sets. Our experimental results demonstrate the efficacy of the proposed cross-lingual approach.
Metrics
Details
- Title
- Cross-lingual sentiment classification with stacked autoencoders
- Creators
- Guangyou Zhou - Central China Normal UniversityZhiyuan Zhu - Chinese Institute of Electronics, Beijing, China 100036Tingting He - Central China Normal UniversityXiaohua Tony Hu - Central China Normal University
- Publication Details
- Knowledge and information systems, v 47(1)
- Publisher
- Springer Nature
- Number of pages
- 18
- Grant note
- CCNU15ZD003 / Fundamental Research Funds for the Central Universities 4144087 / Beijing Natural Science Foundation 61303180; 61272332; 61402191 / National Natural Science Foundation of China; National Natural Science Foundation of China (NSFC) 122D223 / Major Project of National Social Science Found CCF-Tencent Open Research Fund
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Information Science; Mechanical Engineering and Mechanics
- Web of Science ID
- WOS:000371644900002
- Scopus ID
- 2-s2.0-84959470811
- Other Identifier
- 991019173455004721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Information Systems