期刊
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
卷 12, 期 1, 页码 126-140出版社
IEEE COMPUTER SOC
DOI: 10.1109/69.842255
关键词
recurrent neural networks; natural language processing; grammatical inference; government-and-binding theory; gradient descent; simulated annealing; principles-and-parameters framework; automata extraction
This paper examines the inductive inference of a complex grammar with neural networks-specifically, the task considered is that of training a network to classify natural language sentences as grammatical or ungrammatical. thereby exhibiting the same kind of discriminatory power provided by the Principles and Parameters linguistic framework, or Government-and-Binding theory. Neural networks are trained, without the division into learned vs. innate components assumed by Chomsky, in an attempt to produce the same judgments as native speakers on sharply grammatical/ungrammatical data. How a recurrent neural network could possess linguistic capability and the properties of various common recurrent neural network architectures are discussed. The problem exhibits training behavior which is often not present with smaller grammars and training was initially difficult. However, after implementing several techniques aimed at improving the convergence df the gradient descent backpropagation-through-time training algorithm, significant learning was possible. It was found that certain architectures are better able to learn an appropriate grammar. The operation of the networks and their training is analyzed. Finally, the extraction of rules in the form of deterministic finite state automata is investigated.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据