Fusion of multiple features and ranking SVM for web-based English-Chinese OOV term translation

  • Authors:
  • Yuejie Zhang;Yang Wang;Lei Cen;Yanxia Su;Cheng Jin;Xiangyang Xue;Jianping Fan

  • Affiliations:
  • Fudan University;Fudan University;Fudan University;Fudan University;Fudan University;Fudan University;The University of North Carolina at Charlotte

  • Venue:
  • COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
  • Year:
  • 2010

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper focuses on the Web-based English-Chinese OOV term translation pattern, and emphasizes particularly on the translation selection strategy based on the fusion of multiple features and the ranking mechanism based on Ranking Support Vector Machine (Ranking SVM). By utilizing the CoNLL2003 corpus for the English Named Entity Recognition (NER) task and selected new terms, the experiments based on different data sources show the consistent results. Our OOV term translation model can "filter" the most possible translation candidates with better ability. From the experimental results for combining our OOV term translation model with English-Chinese Cross-Language Information Retrieval (CLIR) on the data sets of Text Retrieval Evaluation Conference (TREC), it can be found that the obvious performance improvement for both query translation and retrieval can also be obtained.