BriefGPT.xyz
Jul, 2017
音节感知的神经语言模型：无法打败字符感知的模型
Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones
HTML
PDF
Zhenisbek Assylbekov, Rustem Takhanov, Bagdat Myrzakhmetov, Jonathan N. Washington
TL;DR
比较音节划分和基于字符划分，在词级RNN语言建模的质量提高方面效果不明显。 然而，我们最好的音节感知语言模型表现出与竞争性基于字符模型相当的性能，参数少了18％-33％，并且训练速度提高了1.2-2.2倍。
Abstract
syllabification
does not seem to improve
word-level rnn language modeling
quality when compared to
character-based segmentation
. However,
→