A proposal of 3-dimensional self-organizing memory and its application to knowledge extraction from natural language

Translated title of the contribution: A proposal of 3-dimensional self-organizing memory and its application to knowledge extraction from natural language

Kai Sakakibara, Masafumi Hagiwara

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In this paper, we propose a 3-dimensional self-organizing memory and describe its application to knowledge extraction from natural language. First, the proposed system extracts a relation between words by JUMAN (morpheme analysis system) and KNP (syntax analysis system), and stores it in short-term memory. In the short-term memory, the relations are attenuated with the passage of processing. However, the relations with high frequency of appearance are stored in the long-term memory without attenuation. The relations in the long-term memory are placed to the proposed 3-dimensional self-organizing memory. We used a new learning algorithm called "Potential Firing" in the learning phase. In the recall phase, the proposed system recalls relational knowledge from the learned knowledge based on the input sentence. We used a new recall algorithm called "Waterfall Recall" in the recall phase. We added a function to respond to questions in natural language with "yes/no" in order to confirm the validity of proposed system by evaluating the quantity of correct answers.

Original languageJapanese
Pages (from-to)73-80
Number of pages8
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume21
Issue number1
DOIs
Publication statusPublished - 2006
Externally publishedYes

Fingerprint

Data storage equipment
Learning algorithms
Processing

Keywords

  • 3-dimensional self organizing memory
  • Knowledge representation
  • Natural language processing

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

@article{ef8697f38409463aa97c1e79a4c43b9d,
title = "A proposal of 3-dimensional self-organizing memory and its application to knowledge extraction from natural language",
abstract = "In this paper, we propose a 3-dimensional self-organizing memory and describe its application to knowledge extraction from natural language. First, the proposed system extracts a relation between words by JUMAN (morpheme analysis system) and KNP (syntax analysis system), and stores it in short-term memory. In the short-term memory, the relations are attenuated with the passage of processing. However, the relations with high frequency of appearance are stored in the long-term memory without attenuation. The relations in the long-term memory are placed to the proposed 3-dimensional self-organizing memory. We used a new learning algorithm called {"}Potential Firing{"} in the learning phase. In the recall phase, the proposed system recalls relational knowledge from the learned knowledge based on the input sentence. We used a new recall algorithm called {"}Waterfall Recall{"} in the recall phase. We added a function to respond to questions in natural language with {"}yes/no{"} in order to confirm the validity of proposed system by evaluating the quantity of correct answers.",
keywords = "3-dimensional self organizing memory, Knowledge representation, Natural language processing",
author = "Kai Sakakibara and Masafumi Hagiwara",
year = "2006",
doi = "10.1527/tjsai.21.73",
language = "Japanese",
volume = "21",
pages = "73--80",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "1",

}

TY - JOUR

T1 - A proposal of 3-dimensional self-organizing memory and its application to knowledge extraction from natural language

AU - Sakakibara, Kai

AU - Hagiwara, Masafumi

PY - 2006

Y1 - 2006

N2 - In this paper, we propose a 3-dimensional self-organizing memory and describe its application to knowledge extraction from natural language. First, the proposed system extracts a relation between words by JUMAN (morpheme analysis system) and KNP (syntax analysis system), and stores it in short-term memory. In the short-term memory, the relations are attenuated with the passage of processing. However, the relations with high frequency of appearance are stored in the long-term memory without attenuation. The relations in the long-term memory are placed to the proposed 3-dimensional self-organizing memory. We used a new learning algorithm called "Potential Firing" in the learning phase. In the recall phase, the proposed system recalls relational knowledge from the learned knowledge based on the input sentence. We used a new recall algorithm called "Waterfall Recall" in the recall phase. We added a function to respond to questions in natural language with "yes/no" in order to confirm the validity of proposed system by evaluating the quantity of correct answers.

AB - In this paper, we propose a 3-dimensional self-organizing memory and describe its application to knowledge extraction from natural language. First, the proposed system extracts a relation between words by JUMAN (morpheme analysis system) and KNP (syntax analysis system), and stores it in short-term memory. In the short-term memory, the relations are attenuated with the passage of processing. However, the relations with high frequency of appearance are stored in the long-term memory without attenuation. The relations in the long-term memory are placed to the proposed 3-dimensional self-organizing memory. We used a new learning algorithm called "Potential Firing" in the learning phase. In the recall phase, the proposed system recalls relational knowledge from the learned knowledge based on the input sentence. We used a new recall algorithm called "Waterfall Recall" in the recall phase. We added a function to respond to questions in natural language with "yes/no" in order to confirm the validity of proposed system by evaluating the quantity of correct answers.

KW - 3-dimensional self organizing memory

KW - Knowledge representation

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=30344435936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=30344435936&partnerID=8YFLogxK

U2 - 10.1527/tjsai.21.73

DO - 10.1527/tjsai.21.73

M3 - Article

AN - SCOPUS:30344435936

VL - 21

SP - 73

EP - 80

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 1

ER -