SI Yujing, LI Ta, PAN Jielin, et al., “A Prefix Tree Based n-best List Re-scoring Strategy for Recurrent Neural Network Language Model,” Chinese Journal of Electronics, vol. 23, no. 1, pp. 70-74, 2014,
Citation: SI Yujing, LI Ta, PAN Jielin, et al., “A Prefix Tree Based n-best List Re-scoring Strategy for Recurrent Neural Network Language Model,” Chinese Journal of Electronics, vol. 23, no. 1, pp. 70-74, 2014,

A Prefix Tree Based n-best List Re-scoring Strategy for Recurrent Neural Network Language Model

Funds:  This work is partially supported by the National Natural Science Foundation of China (No.10925419, No.90920302, No.61072124, No.11074275, No.11161140319, No.91120001, No.61271426), the Strategic Priority Research Program of the Chinese Academy of Sciences (No.XDA06030100, No.XDA06030500), the National 863 Program (No.2012AA012503) and the CAS Priority Deployment Project (No.KGZD-EW-103-2).
  • Received Date: 2012-09-01
  • Rev Recd Date: 2013-03-01
  • Publish Date: 2014-01-05
  • In this paper, issues of speeding up Recurrent neural network language model (RNNLM) in the testing phase are explored so that RNNLMs can be used to re-rank a large n-best list in real-time systems which could obtain better performance. A new n-best list rescoring framework, Prefix tree based n-best list re-scoring (PTNR), is proposed to hundred percent eliminate the repeated computations which makes n-best list re-scoring ineffective. At the same time, the bunch mode technique, widely-used in speeding up the training of Feed-forward neural network language model (FF-NNLM), is combined with PTNR and the speed is further improved. Experimental results show that our approach is much faster than basic n-best list re-scoring. Take 1000-best as an example, our approach is almost 11 times faster than the basic n-best list re-scoring.
  • loading
  • R. Rosenfeld,"Two decades of statistical language modeling: Where do we go from here?", Proceedings of the IEEE, Vol.88, No.8, pp.1270-1278, 2000.
    I. Oparin, M. Sundermeyer, H. Ney, J.L. Gauvain,"Performance analysis of neural networks in combination with n-gram language models", Proceedings of ICASSP12, Kyoto, Japan, pp.5005-5008, 2012.
    T. Mikolov, M. Karafiat, L. Burget, J. Cernocky, S. Khudanpur,"Recurrent neural network based language model", Eleventh Annual Conference of the International Speech Communication Association, Chiba, Japan, pp.1045-1048, 2010.
    T. Mikolov, A. Deoras, S. Kombrink, L. Burget, J. Cernocky,"Empirical evaluation and combination of advanced language modeling techniques", Twelfth Annual Conference of the International Speech Communication Association, Florence, Italy, pp.605-608, 2011.
    S. Kombrink, T. Mikolov, M. Karafiat, L. Burget,"Recurrent neural network based language modeling in meeting recognition", Twelfth Annual Conference of the International Speech Communication Association, Florence, Italy, pp.2877-2880, 2011.
    H. Schwenk,"Continuous space language models", Computer Speech & Language, Vol.21, No.3, pp.492-518, 2007.
    T. Mikolov, S. Kombrink, L. Burget, J. Cernocky, S. Khudanpur,"Extensions of recurrent neural network language model", 2011 IEEE International Conference on. Acoustics, Speech and Signal Processing (ICASSP), IEEE, Prague, Czech Republic, pp.5528-5531, 2011.
    T. Mikolov, A. Deoras, D. Povey, L. Burget,"Strategies for training large scale neural network language models", ASRU 2011, Hawaii, USA, pp.196-201, 2011.
    K. Chen, W. Bao, H. Chi,"Speed up training of the recurrent neural network based on constrained optimization techniques", Journal of Computer Science and Technology, Vol.11, No.6, pp.581-588, 1996.
    G. Lecorve, P. Motlicek,"Conversion of recurrent neural network language models to weighted finite state transducers for automatic speech recognition", Eleventh Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, pp.5032-5035, 2012.
    A. Deoras, T. Mikolov, K. Church,"A fast re-scoring strategy to capture long-distance dependencies", Proceedings of EMNLP, Edinburgh, UK, pp.1116-1127, 2011.
    Y. Si, T. Li, S. Cai, J. Pan, Y. Yan,"Recurrent neural network language model in mandarin voice input system", 2012 Eighth International Conference on. Natural Computation (ICNC), IEEE, Chongqing, China, pp.270-274, 2012.
    J. Bilmes, K. Asanovic, C.W. Chin et al.,"Using phipac to speed error back-propagation learning", ICASSP-97, IEEE, Vol.5, pp.4153-4156, 1997.
    K. Heafield,"Kenlm: Faster and smaller language modelqueries", Proceedings of the Sixth Workshop on Statistical Machine Translation, Edinburgh, UK, pp.187-197, 2011.
    J. Shao, T. Li, Q. Zhang, Q. Zhao, Y. Yan,"A one-pass realtime decoder using memory-efficient state network", IEICE TRANSACTIONS on Information and Systems, Vol.91, No.3, pp.529-537, 2008.
    A. Stolcke et al.,"Srilm-an extensible language modeling toolkit", Proceedings of the International Conference on Spoken Language Processing, Vol.2, pp.901-904, 2002.
    M. Boden,"A guide to recurrent neural networks andbackpropagation", Dallas Project, Vol.3, No.2, pp.1-10, 2002.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (604) PDF downloads(1402) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return