会议论文

Zhou, Guangyou

英文

PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI)

2015

1426-1432

1st International Workshop on Social Influence Analysis / 24th International Joint Conference on Artificial Intelligence (IJCAI)

JUL 25-31, 2015

Buenos Aires, ARGENTINA

[Zhou, Guangyou;He, Tingting] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.^[Zhao, Jun] CASIA, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China.^[Wu, Wensheng] Univ Southern Calif, Comp Sci Dept, Los Angeles, CA 90089 USA.

Yang, Q Wooldridge, M

ALBERT-LUDWIGS UNIV FREIBURG GEORGES-KOHLER-ALLEE, INST INFORMATIK, GEB 052, FREIBURG, D-79110, GERMANY

IJCAI-INT JOINT CONF ARTIF INTELL

978-1-57735-738-4

National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61303180, 61272332]; Beijing Natural Science FoundationBeijing Natural Science Foundation [4144087]; Major Project of National Social Science Found [122D223]; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [CCNU15ZD003]; CCF-Tencent Open Research Fund

本校为第一且通讯机构

Cross-lingual sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of data in a label-scarce target language by exploiting labeled data from a label-rich language. The fundamental challenge of cross-lingual learning stems from a lack of overlap between the feature spaces of the source language data and that of the target language data. To address this challenge, previous work in the literature mainly relies on the large amount of bilingual parallel corpora to bridge the language gap. In many real applications, however, it is often the case that...