Browse wiki

Jump to: navigation, search
Natural language processing neural network for analogical inference
Abstract In this paper, we propose a novel neural nIn this paper, we propose a novel neural network which can learn knowledge from natural language documents and can perform analogy. The conventional neural networks can use only the information the networks learned: knowledge acquisition has been a serious problem. The proposed network solves it by using a large scale dictionary named Google N-gram. In the preprocessing, natural language documents are analyzed by a Japanese dependency structure analyzer named Cabocha. The results are used in the network connection learning. In the analogy process, firing patterns of neurons are memorized in memory parts. When a similar firing pattern is appeared, a memorized pattern is retrieved. This process enables analogical inference. Three kinds of experiments were carried out using goo encyclopedia and Wikipedia as knowledge source. Superior performance of the proposed neural network has been confirmed.roposed neural network has been confirmed.
Abstractsub In this paper, we propose a novel neural nIn this paper, we propose a novel neural network which can learn knowledge from natural language documents and can perform analogy. The conventional neural networks can use only the information the networks learned: knowledge acquisition has been a serious problem. The proposed network solves it by using a large scale dictionary named Google N-gram. In the preprocessing, natural language documents are analyzed by a Japanese dependency structure analyzer named Cabocha. The results are used in the network connection learning. In the analogy process, firing patterns of neurons are memorized in memory parts. When a similar firing pattern is appeared, a memorized pattern is retrieved. This process enables analogical inference. Three kinds of experiments were carried out using goo encyclopedia and Wikipedia as knowledge source. Superior performance of the proposed neural network has been confirmed.roposed neural network has been confirmed.
Bibtextype inproceedings  +
Doi 10.1109/IJCNN.2010.5596742  +
Has author Saito M. + , Hagiwara M. +
Has extra keyword Analogy process + , Dependency structures + , Firing patterns + , Knowledge sources + , NAtural language processing + , Natural languages + , Network connection + , Novel neural network + , Wikipedia + , Computational linguistics + , Knowledge acquisition + , Natural language processing systems + , Neural networks +
Isbn 9781424469178  +
Language English +
Number of citations by publication 0  +
Number of references by publication 0  +
Published in Proceedings of the International Joint Conference on Neural Networks +
Title Natural language processing neural network for analogical inference +
Type conference paper  +
Year 2010 +
Creation dateThis property is a special property in this wiki. 8 November 2014 06:36:58  +
Categories Publications without keywords parameter  + , Publications without license parameter  + , Publications without remote mirror parameter  + , Publications without archive mirror parameter  + , Publications without paywall mirror parameter  + , Conference papers  + , Publications without references parameter  + , Publications  +
Modification dateThis property is a special property in this wiki. 8 November 2014 06:36:58  +
DateThis property is a special property in this wiki. 2010  +
hide properties that link here 
Natural language processing neural network for analogical inference + Title
 

 

Enter the name of the page to start browsing from.