نویسنده : دکتر مهرنوش صدر زاده - 1393/09/25

برای دریافت فایل تصویری به ادامه مطلب مراجعه کنید

Abstract: Formal models of natural language are neither recent nor

rare: one can argue that Aristotle's syllogistic logic was the first such

attempt; there is the work of Chomsky on generative grammars and

the more algebraic work of Lambek (the syntactic calculus and its

various forms), combinatorial work of Steedman (CCG), Discourse

Representation Theory of Kamp and so on. But all of these formal

systems are based on a denotational set-theoretic semantics. More

recent approaches to semantics of natural language argue that

pragmatism also plays a crucial role and that meaning representations

of words should be based on the contexts in which they often occur;

here, various statistical measures are developed to retrieve such

information from large corpora of real natural language texts and to

reason about them. A popular formal framework is vector space

models. These provide a solid base for word meaning, but it is less

clear how to extend them to phrases and sentences. In joint ongoing

work with Clark and Coecke we provide a setting on how to use linear

algebraic operations inspired by category theoretical models of vector

spaces and develop a solution. Here, empirical data from corporal and

experimental analysis is an essential tool to verify the theoretical

predictions of the models


 برای دریافت فایل تصویری سخنرانی ومتن از لینک زیر استفاده کنید

متن پاورپوینت


بخش اول فایل تصویری


بخش دوم فایل تصویری


نظرات کاربران
   
   
   
مطالب مرتبط

© Company 2013