An english neural network that learns texts, finds hidden knowledge, and answers questions

Yuanzhi Ke, Masafumi Hagiwara

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.

Original languageEnglish
Pages (from-to)229-242
Number of pages14
JournalJournal of Artificial Intelligence and Soft Computing Research
Volume7
Issue number4
DOIs
Publication statusPublished - 2017 Oct 1

Fingerprint

Neural Networks
Neural networks
Labels
Neurons
Neuron
Semantics
Semantic Network
Thing
Exercise
Experiment
Experiments
Text
Knowledge
Model

Keywords

  • Natural language processing
  • Natural language understanding
  • Neural network
  • Question answering

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Information Systems
  • Modelling and Simulation

Cite this

@article{3afed0e4ad7d4dc0bb74bf660927a9a1,
title = "An english neural network that learns texts, finds hidden knowledge, and answers questions",
abstract = "In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.",
keywords = "Natural language processing, Natural language understanding, Neural network, Question answering",
author = "Yuanzhi Ke and Masafumi Hagiwara",
year = "2017",
month = "10",
day = "1",
doi = "10.1515/jaiscr-2017-0016",
language = "English",
volume = "7",
pages = "229--242",
journal = "Journal of Artificial Intelligence and Soft Computing Research",
issn = "2083-2567",
publisher = "De Gruyter Open Ltd.",
number = "4",

}

TY - JOUR

T1 - An english neural network that learns texts, finds hidden knowledge, and answers questions

AU - Ke, Yuanzhi

AU - Hagiwara, Masafumi

PY - 2017/10/1

Y1 - 2017/10/1

N2 - In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.

AB - In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.

KW - Natural language processing

KW - Natural language understanding

KW - Neural network

KW - Question answering

UR - http://www.scopus.com/inward/record.url?scp=85019131993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019131993&partnerID=8YFLogxK

U2 - 10.1515/jaiscr-2017-0016

DO - 10.1515/jaiscr-2017-0016

M3 - Article

VL - 7

SP - 229

EP - 242

JO - Journal of Artificial Intelligence and Soft Computing Research

JF - Journal of Artificial Intelligence and Soft Computing Research

SN - 2083-2567

IS - 4

ER -