通过不同语言域的同步神经网络模型学习结构的对应关系][Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models]

通过不同语言域的同步神经网络模型学习结构的对应关系 Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models


课程网址:	http://videolectures.net/nipsworkshops2012_gouws_neural_language/
主讲教师:	Stephan Gouws
开课单位:	斯泰伦博斯大学
开课时间:	2013-01-11
课程语种:	英语
中文简介:	在同步神经语言模型训练的基础上，提出了一种新的学习两个语言域结构对应关系的框架。我们的初步结果表明，我们的框架可以成功地用于学习跨不同领域的相关对象的相似特征表示，因此可能是跨不同语言领域转移学习的一种成功方法。
课程简介:	We introduce a novel framework for learning structural correspondences between two linguistic domains based on training synchronous neural language models with co-regularization on both domains simultaneously. We show positive preliminary results indicating that our framework can be successfully used to learn similar feature representations for correlated objects across different domains, and may therefore be a successful approach for transfer learning across different linguistic domains.
关键词:	正规化训练; 神经语言模型; 不同语言域的转移学习
课程来源:	视频讲座网
最后编审:	2020-06-02：毛岱琦(课程编辑志愿者)
阅读次数:	55

境外开放课程导航