Extraction of chinese multiword expressions based on artificial neural network with feedbacks

  • Authors:
  • Yiwen Fu;Naisheng Ge;Zhongguang Zheng;Shu Zhang;Yao Meng;Hao Yu

  • Affiliations:
  • Fujitsu R&D Center Co.,Ltd., Beijing, P.R. China;Fujitsu R&D Center Co.,Ltd., Beijing, P.R. China;Fujitsu R&D Center Co.,Ltd., Beijing, P.R. China;Fujitsu R&D Center Co.,Ltd., Beijing, P.R. China;Fujitsu R&D Center Co.,Ltd., Beijing, P.R. China;Fujitsu R&D Center Co.,Ltd., Beijing, P.R. China

  • Venue:
  • PRICAI'12 Proceedings of the 12th Pacific Rim international conference on Trends in Artificial Intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Multiword Expressions present idiosyncratic features in the application of Natural Language Processing. This paper focuses on Multiword Expressions extraction from bilingual corpus with alignment information constructed by Statistical Machine Translation (SMT) and word alignment method. A pattern based extraction system and an Artificial Neural Network (ANN) with feedback are applied for extracting MWEs. The results show that both of these approaches can achieve satisfying performance.