Performance analysis of FFNN-based language model in contrast with n-gram

  • Kim, Kwang-Ho
  • Lee, Donghyun
  • Lim, Minkyu
  • Ryang, Minho
  • Jang, Gil-Jin
  • ... Kim, J. -H.
  • 외 1명
Citations

SCOPUS

0

초록

In this paper, we analyze the performance of feed forward neural network (FFNN)-based language model in contrast with n-gram. The probability of n-gram language model was estimated based on the statistics of word sequences. The FFNN-based language model was structured by three hidden layers, 500 hidden units per each hidden layer, and 30 dimension word embedding. The performance of FFNN-based language model is better than that of n-gram by 1.5 % in terms of WER on the English WSJ domain. © Springer International Publishing Switzerland 2015. All rights are reserved.

키워드

Feed forward neural networkLanguage modelN-GramPerformance analysis
제목
Performance analysis of FFNN-based language model in contrast with n-gram
저자
Kim, Kwang-HoLee, DonghyunLim, MinkyuRyang, MinhoJang, Gil-JinPark, Jeong-SikKim, J. -H.
DOI
10.1007/978-3-319-19291-8_25
발행일
2015-10-29
유형
Book Chapter
저널명
Natural Language Dialog Systems and Intelligent Assistants
페이지
253 ~ 256