Domain Adaptation on Personalized Neural Netowrk Based Language Models
Date Issued
2014
Date
2014
Author(s)
Liang, An-Chun
Abstract
Personalized language models play an important role in many real world applications as the online social network services blossom. Neural network based language models are increasingly popular and outperforming traditional n-gram language models recently. To deal with the data sparseness problem in training the personalized language models, we propose a novel domain adap- tation method based on regularization on distributed word representations of neural network based language models from other models in the social net- work. Our method does not requires the text data of the source domain but only needs the parameters of the source model. Thus it requires less mem- ory and disk space, which is limited on smart-phone devices. We show that our method is more robust and is able to transfer knowledge from dissimilar domains during cross-individual adaptation. Our method is able to combine with the linear interpolation adaptation methods to make further improvement in cross-domain adaptation.
Subjects
領域適應
語言模型
類神經網路語言模型
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-103-R01922038-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):b7585debe0349607c99fa33aff033c2e