Conference proceeding
A Feature-Reinforcement-Based Approach for Supporting Poly-Lingual Category Integration
DESIGNING E-BUSINESS SYSTEMS, v 22
01 Jan 2009
Abstract
Document-category integration (or category integration for short) is fundamental to many e-commerce applications, including information integration along supply chains and information aggregation by intermediaries. Because of the trend of globalization, the requirement for category integration has been extended from Monolingual to poly-lingual settings. Poly-lingual category, interaction (PLCI) aims to integrate two document catalogs, each of which consists of documents in a mix of languages. Several category integration technique have been proposed in the literature, but these techniques focus only on monolingual category integration rather than PLCI. In this study, we propose a feature-reinforcement-based PLCI (namely, FR-PLCI) technique that takes into account the master documents of all languages when integrating source documents, (in the source catalog) written in a specific language into the master catalog. Using the monolingual category integration (MnCI) technique as a performance benchmark, our empirical evaluation results show that Our proposed FR-PLCI technique achieves better Integration accuracy than MnCI does in both English and Chinese category integration tasks.
Metrics
4 Record Views
Details
- Title
- A Feature-Reinforcement-Based Approach for Supporting Poly-Lingual Category Integration
- Creators
- Chih-Ping Wei - National Tsing Hua UniversityChao-Chi Chen - National Tsing Hua UniversityTsang-Hsiang Cheng - Southern Taiwan University of Science and TechnologyChristopher C. Yang - Drexel University
- Contributors
- C Weinhardt (Editor)S Luckner (Editor)J Stober (Editor)
- Publication Details
- DESIGNING E-BUSINESS SYSTEMS, v 22
- Series
- Lecture Notes in Business Information Processing
- Publisher
- Springer Nature
- Number of pages
- 2
- Grant note
- NSC 96-2416-H-218-010 / National Science Council of the Republic of China; Ministry of Science and Technology, Taiwan
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science
- Web of Science ID
- WOS:000268378000014
- Scopus ID
- 2-s2.0-70349538815
- Other Identifier
- 991019170590004721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Business
- Computer Science, Hardware & Architecture
- Computer Science, Information Systems