扎根语言学习Grounded Language Learning |
|
课程网址: | http://videolectures.net/aaai2013_mooney_language_learning/ |
主讲教师: | Raymond J. Mooney |
开课单位: | 德克萨斯大学 |
开课时间: | 2013-11-14 |
课程语种: | 英语 |
中文简介: | 计算语言学中大多数语义学方法都是用词或抽象符号来表示含义。扎实的语言研究将自然语言的含义基于(真实或虚拟)世界中的感知和/或动作。机器学习已成为构建自然语言系统的最有效方法。但是,当前的方法需要大量费力的注释训练数据。理想情况下,通过在相关但模棱两可的环境中接触语言,计算机将能够像儿童一样获得语言,从而将其学习基于感知和行动。我们将回顾基础语言学习的最新研究并讨论未来的方向。 p> |
课程简介: | Most approaches to semantics in computational linguistics represent meaning in terms of words or abstract symbols. Grounded-language research bases the meaning of natural language on perception and/or action in the (real or virtual) world. Machine learning has become the most effective approach to constructing natural-language systems; however, current methods require a great deal of laboriously annotated training data. Ideally, a computer would be able to acquire language like a child, by being exposed to language in the context of a relevant but ambiguous environment, thereby grounding its learning in perception and action. We will review recent research in grounded language learning and discuss future directions. |
关 键 词: | 计算语言学; 机器学习 |
课程来源: | 视频讲座网 |
数据采集: | 2020-11-01:zyk |
最后编审: | 2020-11-01:zyk |
阅读次数: | 122 |