From simple associations to the building blocks of language: Modeling meaning in memory with the HAL model
From simple associations to the building blocks of language: Modeling meaning in memory with the HAL model
复制标题
DOI：
10.3758/bf03200643
复制
发表时间：
1998-05-01
期刊：
影响因子：
--
通讯作者：
Burgess, C
中科院分区：
文献类型：
--
作者：
Burgess, C
本文提出了一种简单的情景联想如何转化为语义和语法范畴知识的理论方法。该方法是在记忆的超空间语言模拟(HAL)模型中实现的，该模型使用一种简单的全局共现学习算法来编码单词出现的上下文。这种编码是在高维语境空间中形成意义表征的基础。结果表明，这个简单的过程最终可以为语言理解系统提供理解过程中所需的语义和语法信息。
This paper presents a theoretical approach of how simple, episodic associations are transduced into semantic and grammatical categorical knowledge. The approach is implemented in the hyperspace analogue to language (HAL) model of memory, which uses a simple global co-occurrence learning algorithm to encode the context in which words occur. This encoding is the basis for the formation of meaning representations in a high-dimensional context space. Results are presented, and the argument is made that this simple process can ultimately provide the language-comprehension system with semantic and grammatical information required in the comprehension process.