JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Class Language Model based on Word Embedding and POS Tagging
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
 Title & Authors
Class Language Model based on Word Embedding and POS Tagging
Chung, Euisok; Park, Jeon-Gue;
 
 Abstract
Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.
 Keywords
word embedding;class LM;part-of-speech tagging based class LM;RNN LM;
 Language
Korean
 Cited by
 References
1.
Y. Bengio, R. Ducharme, P. Vincent, A neural probabilistic language model, Journal of Machine Learning Research, 3:1137-1155, 2003.

2.
T. Mikolov, A. Deoras, D. Povey, L. Burget and J. Cernocky, "Strategies for training large scale neural network language models," Automatic Speech Recognition and Understanding (ASRU), 2011.

3.
T. Mikolov, K. Chen, G. Corrado and J. Dean, "Efficient Estimation of Word Representations in Vector Space," International Conference of Learning Representations (ICLR), 2013.

4.
A. Neelakantan, J. Shankar, A. Passos and A. McCallum, "Efficient non-parametric estimation of multiple embeddings per word in vector space," Empirical Methods on Natural Language Processing (EMNLP), 2014.

5.
E. Chung and J. Park, "Word Embedding based Class Language Model," Human & Cognitive Language Technology (HCLT), 2015.

6.
S. F. Chen and J. Goodman, "An empirical study of smoothing techniques for language modeling," Technical Report TR-10-98, Computer Science Group, Harvard University, 1998.

7.
X. Rong, "word2vec Explained: Deriving Mikolov et al.'s Negative-Sampling Word-Embedding Method," arXiv:1402.3722 [cs.CL], 2014.

8.
X. Rong, "word2vec Parameter Learning Explained," arXiv:1411.2738 [cs.CL], 2016.

9.
C. Lee, J. Kim and J. Kim, "Korean Dependency Parsing using Deep Learning," Human & Cognitive Language Technology (HCLT), 2014.

10.
D. Q. Nguyen, D. D. Pham and S. B. Pham, "RDRPOSTagger: A Ripple Down Rules-based Part-Of-Speech Tagger," European Chapter of the Association for Computational Linguistics (EACL), pp. 17-20, 2014.