图 书 馆
统计语言建模的三种新图形模型Three New Graphical Models for Statistical Language Modelling |
|
| 课程网址: | http://videolectures.net/icml07_mnih_tngm/ |
| 主讲教师: | Andriy Mnih |
| 开课单位: | 多伦多大学 |
| 开课时间: | 2007-06-23 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficulties caused by data sparsity. We propose three new probabilistic language models that define the distribution of the next word in a sequence given several preceding words by using distributed representations of those words. We show how real-valued distributed representations for words can be learned at the same time as learning a large set of stochastic binary hidden features that are used to predict the distributed representation of the next word from previous distributed representations. Adding connections from the previous states of the binary hidden features improves performance as does adding direct connections between the real-valued distributed representations. One of our models significantly outperforms the very best ngram models. |
| 关 键 词: | 统计语言; n克模型; 参数模型 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-17：lxf |
| 阅读次数: | 126 |