Loading...

Unilateral semi-supervised learning of extended hidden vector state for Persian language understanding

Jabbari, F ; Sharif University of Technology | 2011

1006 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/NLPKE.2011.6138187
  3. Publisher: 2011
  4. Abstract:
  5. The key element of a spoken dialogue system is Spoken Language Understanding (SLU) part. HVS and EHVS are two most popular statistical methods employed to implement the SLU part which need lightly annotated data. Since annotation is a time consuming, we present a novel semi-supervised learning for EHVS to reduce the human labeling effort using two different statistical classifiers, SVM and KNN. Experiments are done on a Persian corpus, the University Information Kiosk corpus. The experimental results show improvements in performance of semi-supervised EHVS, trained by both labeled and unlabeled data, compared to EHVS trained by just initially labeled data. The performance of EHVS improves 13.41% in the case of SVM classifier and 5.16% in the case of KNN. This demonstrates effectiveness and feasibility of the proposed approach
  6. Keywords:
  7. Extended hidden vector state ; Hidden vectors ; Information kiosks ; Key elements ; Labeled and unlabeled data ; Labeled data ; Language understanding ; Persians ; Semi-supervised ; Semi-supervised learning ; Spoken dialogue system ; Spoken language understanding ; Statistical classifier ; SVM classifiers ; Classification (of information) ; Computational linguistics ; Diagnostic radiography ; Knowledge engineering ; Natural language processing systems ; Speech processing ; Supervised learning
  8. Source: NLP-KE 2011 - Proceedings of the 7th International Conference on Natural Language Processing and Knowledge Engineering, 27 November 2011 through 29 November 2011, Tokushima ; 2011 , Pages 165-168 ; 9781612847283 (ISBN)
  9. URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6138187