Natural language neural network and its application to question-answering system

Tsukasa Sagara, Masafumi Hagiwara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper proposes a novel neural network to treat natural language. Most of the conventional neural networks can only process sentences consisted of a few words, and their applications are very simple such as metaphor understanding. The proposed network can process many complicated sentences and can be used as an associative memory and a question-answering system. The proposed network is composed of 3 layers and one network: Sentence Layer, Knowledge Layer, Deep Case Layer and Dictionary Network. The input sentences are divided into knowledge units and stored in the Knowledge Layer. The Deep Case Layer play an important role to process the knowledge units properly. The Dictionary Network also plays an important role as a knowledge based. We have carried out several experiments and they have shown that the proposed neural network has superior performances as an associative memory and a question-answering system. Especially as a question-answering system, the performance is very close to the elaborated system based on artificial intelligence.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
DOIs
Publication statusPublished - 2012
Event2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD, Australia
Duration: 2012 Jun 102012 Jun 15

Other

Other2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
CountryAustralia
CityBrisbane, QLD
Period12/6/1012/6/15

Fingerprint

Glossaries
Neural networks
Data storage equipment
Network layers
Artificial intelligence
Experiments

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Sagara, T., & Hagiwara, M. (2012). Natural language neural network and its application to question-answering system. In Proceedings of the International Joint Conference on Neural Networks [6252553] https://doi.org/10.1109/IJCNN.2012.6252553

Natural language neural network and its application to question-answering system. / Sagara, Tsukasa; Hagiwara, Masafumi.

Proceedings of the International Joint Conference on Neural Networks. 2012. 6252553.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sagara, T & Hagiwara, M 2012, Natural language neural network and its application to question-answering system. in Proceedings of the International Joint Conference on Neural Networks., 6252553, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, Australia, 12/6/10. https://doi.org/10.1109/IJCNN.2012.6252553
Sagara T, Hagiwara M. Natural language neural network and its application to question-answering system. In Proceedings of the International Joint Conference on Neural Networks. 2012. 6252553 https://doi.org/10.1109/IJCNN.2012.6252553
Sagara, Tsukasa ; Hagiwara, Masafumi. / Natural language neural network and its application to question-answering system. Proceedings of the International Joint Conference on Neural Networks. 2012.
@inproceedings{5452615b563d42d088279ceee2440f78,
title = "Natural language neural network and its application to question-answering system",
abstract = "This paper proposes a novel neural network to treat natural language. Most of the conventional neural networks can only process sentences consisted of a few words, and their applications are very simple such as metaphor understanding. The proposed network can process many complicated sentences and can be used as an associative memory and a question-answering system. The proposed network is composed of 3 layers and one network: Sentence Layer, Knowledge Layer, Deep Case Layer and Dictionary Network. The input sentences are divided into knowledge units and stored in the Knowledge Layer. The Deep Case Layer play an important role to process the knowledge units properly. The Dictionary Network also plays an important role as a knowledge based. We have carried out several experiments and they have shown that the proposed neural network has superior performances as an associative memory and a question-answering system. Especially as a question-answering system, the performance is very close to the elaborated system based on artificial intelligence.",
author = "Tsukasa Sagara and Masafumi Hagiwara",
year = "2012",
doi = "10.1109/IJCNN.2012.6252553",
language = "English",
isbn = "9781467314909",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Natural language neural network and its application to question-answering system

AU - Sagara, Tsukasa

AU - Hagiwara, Masafumi

PY - 2012

Y1 - 2012

N2 - This paper proposes a novel neural network to treat natural language. Most of the conventional neural networks can only process sentences consisted of a few words, and their applications are very simple such as metaphor understanding. The proposed network can process many complicated sentences and can be used as an associative memory and a question-answering system. The proposed network is composed of 3 layers and one network: Sentence Layer, Knowledge Layer, Deep Case Layer and Dictionary Network. The input sentences are divided into knowledge units and stored in the Knowledge Layer. The Deep Case Layer play an important role to process the knowledge units properly. The Dictionary Network also plays an important role as a knowledge based. We have carried out several experiments and they have shown that the proposed neural network has superior performances as an associative memory and a question-answering system. Especially as a question-answering system, the performance is very close to the elaborated system based on artificial intelligence.

AB - This paper proposes a novel neural network to treat natural language. Most of the conventional neural networks can only process sentences consisted of a few words, and their applications are very simple such as metaphor understanding. The proposed network can process many complicated sentences and can be used as an associative memory and a question-answering system. The proposed network is composed of 3 layers and one network: Sentence Layer, Knowledge Layer, Deep Case Layer and Dictionary Network. The input sentences are divided into knowledge units and stored in the Knowledge Layer. The Deep Case Layer play an important role to process the knowledge units properly. The Dictionary Network also plays an important role as a knowledge based. We have carried out several experiments and they have shown that the proposed neural network has superior performances as an associative memory and a question-answering system. Especially as a question-answering system, the performance is very close to the elaborated system based on artificial intelligence.

UR - http://www.scopus.com/inward/record.url?scp=84865066292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865066292&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2012.6252553

DO - 10.1109/IJCNN.2012.6252553

M3 - Conference contribution

AN - SCOPUS:84865066292

SN - 9781467314909

BT - Proceedings of the International Joint Conference on Neural Networks

ER -