Work

Transfer Learning for Cross-Language Text Categorization through Active Correspondences Construction

Year: 2016

Type: conference-paper

Abstract: Most existing heterogeneous transfer learning (HTL) methods for cross-language text classification rely on sufficient cross-domain instance correspondences to learn a mapping across heterogeneous feature spaces, and assume that such correspondences are given in advance. However, in practice, correspondences between domains are usually unknown. In this case, extensively manual efforts are required to establish accurate correspondences across multilingual documents based on their content and meta-information. In this paper, we present a general framework to integrate active learning to construct correspondences between heterogeneous domains for HTL, namely HTL through active correspondences construction (HTLA). Based on this framework, we develop a new HTL method. On top of the new HTL method, we further propose a strategy to actively construct correspondences between domains. Extensive experiments are conducted on various multilingual text classification tasks to verify the effectiveness of HTLA.

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v30i1.10211

Authors: Joey Zhou, Sinno Pan, Ivor Tsang, Shen-Shyang Ho

Institutions: Institute of High Performance Computing, Nanyang Technological University

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: Nanyang Technological University, Ministry of Education, India, Australian Research Council

Awards: G5280407516, Interaction Mining for Cyberbullying Detection on Social Networks, Big Data Machines: Internet-Scale Machine Learning Techniques to Combat the Curse of Big Data, G8771026661