给你和另一位提问的层主提供参考资料：Peter Gärdenfors 的《Conceptual Spaces - the Geometry of Thought》，MIT Press 2000 年出版（2004 年平装本）。读起来非常轻松。几何意义理论的问题在于 compositionality 和 quantification——如何获得……的表达能力
References for you and the other poster who asked: Peter Gärdenfors: Conceptual Spaces - the Geometry of Thought. MIT Press 2000 (Paperback 2004). It is very easy reading. The problems of geometric meaning theory are compositionality and quantification - how to get the expressivity of…
……我听过关于水果沙拉到底算不算沙拉的整场讲座，还有三明治的那些例子。在我看来，几何意义理论能相当好地捕捉到相关问题，比如 Conceptual Spaces。在语言学中，prototype theory 和相关方法从 20 世纪 70 年代起就在处理这些问题了。这并不是说问题已经解决，但在我看来，许多问题都源于人为聚焦在……
…I've heard whole lectures about whether fruit salad really is a salad, and the sandwich examples, too. In my opinion, geometric meaning theories capture the associated problems fairly well, for example Conceptual Spaces. In linguistics, prototype theory and related approaches have dealt with them since the 1970s. That is not to say that the problems are solved but in my opinion many problems come from an artificial focus…
thanks , this is relevant to Rosch's prototype theory I've been reading on recently https://en.wikipedia.org/wiki/Prototype_theory, and also Gärdenfors' conceptual spaces, which is more modern and has some neurophysiological basis: https://en.wikipedia.org/wiki/Conceptual_space OP, sorry for hijacking the thread
…general idea (using word frequencies in context) is Firth's distributional hypothesis [0]. Related to this is the idea of a distributional representation which is covered by Gardenfors in his book on conceptual spaces. For word2vec and such, several papers in this year's TACL explain why these methods should work [1,2]. [0] https://www.aclweb.org/aclwiki/index.php?title=Distributiona... [1] https://transacl.org/ojs/index.php/tacl/article/viewFile/742... [2]https://transacl.org/ojs/index.php/tacl/article/viewFile/809...
…out of it was to stop thinking of it as a chatbot or knowledge engine, and instead try to model how it actually works on a structural level. The closest parallel I’ve found is Peter Gärdenfors’ work on conceptual spaces, where meaning isn’t symbolic but geometric. Fedorenko’s research on predictive sequencing in the brain fits too. In both cases, the idea is that language follows a trajectory through a shaped mental…
给你和另一位提问的层主提供参考资料：Peter Gärdenfors 的《Conceptual Spaces - the Geometry of Thought》，MIT Press 2000 年出版（2004 年平装本）。读起来非常轻松。几何意义理论的问题在于 compositionality 和 quantification——如何获得……的表达能力
References for you and the other poster who asked: Peter Gärdenfors: Conceptual Spaces - the Geometry of Thought. MIT Press 2000 (Paperback 2004). It is very easy reading. The problems of geometric meaning theory are compositionality and quantification - how to get the expressivity of…
……我听过关于水果沙拉到底算不算沙拉的整场讲座，还有三明治的那些例子。在我看来，几何意义理论能相当好地捕捉到相关问题，比如 Conceptual Spaces。在语言学中，prototype theory 和相关方法从 20 世纪 70 年代起就在处理这些问题了。这并不是说问题已经解决，但在我看来，许多问题都源于人为聚焦在……
…I've heard whole lectures about whether fruit salad really is a salad, and the sandwich examples, too. In my opinion, geometric meaning theories capture the associated problems fairly well, for example Conceptual Spaces. In linguistics, prototype theory and related approaches have dealt with them since the 1970s. That is not to say that the problems are solved but in my opinion many problems come from an artificial focus…
多谢，这和我最近在读的 Rosch 的 prototype theory 很相关（https://en.wikipedia.org/wiki/Prototype_theory），还有 Gärdenfors 的 conceptual spaces，后者更现代一些，并且有一定的神经生理学基础：https://en.wikipedia.org/wiki/Conceptual_space 楼主抱歉，歪楼了哈
thanks , this is relevant to Rosch's prototype theory I've been reading on recently https://en.wikipedia.org/wiki/Prototype_theory, and also Gärdenfors' conceptual spaces, which is more modern and has some neurophysiological basis: https://en.wikipedia.org/wiki/Conceptual_space OP, sorry for hijacking the thread
……核心思想（在上下文中使用词频）是 Firth 的 distributional hypothesis [0]。与此相关的是 distributional representation 的概念，Gardenfors 在关于 conceptual spaces 的书中对此做过探讨。关于 word2vec 等模型，今年 TACL 上的几篇论文解释了为什么这些方法会奏效 [1,2]。[0] https://www.aclweb.org/aclwiki/index.php?title=Distributiona... [1] https://transacl.org/ojs/index.php/tacl/article/viewFile/742... [2]https://transacl.org/ojs/index.php/tacl/article/viewFile/809...
…general idea (using word frequencies in context) is Firth's distributional hypothesis [0]. Related to this is the idea of a distributional representation which is covered by Gardenfors in his book on conceptual spaces. For word2vec and such, several papers in this year's TACL explain why these methods should work [1,2]. [0] https://www.aclweb.org/aclwiki/index.php?title=Distributiona... [1] https://transacl.org/ojs/index.php/tacl/article/viewFile/742... [2]https://transacl.org/ojs/index.php/tacl/article/viewFile/809...
……摆脱这种思维的方式，就是不再把它看作 chatbot 或知识引擎，而是试着在结构层面建模它的实际运作机制。我找到的最贴切的类比是 Peter Gärdenfors 关于 conceptual spaces 的研究，在其中意义不是符号化的，而是几何形态的。Fedorenko 关于大脑中 predictive sequencing 的研究也契合这一点。这两种理论的核心思想都是：语言沿着特定轨迹穿过成型的心智……
…out of it was to stop thinking of it as a chatbot or knowledge engine, and instead try to model how it actually works on a structural level. The closest parallel I’ve found is Peter Gärdenfors’ work on conceptual spaces, where meaning isn’t symbolic but geometric. Fedorenko’s research on predictive sequencing in the brain fits too. In both cases, the idea is that language follows a trajectory through a shaped mental…