Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network
Abstract
In this paper, we propose an efficient transfer leaning methods for training a personalized language model using a recurrent neural network with long short-term memory architecture. With our proposed fast transfer learning schemes, a general language model is updated to a personalized language model with a small amount of user data and a limited computing resource. These methods are especially useful for a mobile device environment while the data is prevented from transferring out of the device for privacy purposes. Through experiments on dialogue data in a drama, it is verified that our transfer learning methods have successfully generated the personalized language model, whose output is more similar to the personal language style in both qualitative and quantitative aspects.
Cite
@article{arxiv.1701.03578,
title = {Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network},
author = {Seunghyun Yoon and Hyeongu Yun and Yuna Kim and Gyu-tae Park and Kyomin Jung},
journal= {arXiv preprint arXiv:1701.03578},
year = {2017}
}
Comments
AAAI workshop on Crowdsourcing, Deep Learning and Artificial Intelligence Agents, Feb 2017, San Francisco CA, USA