Tibetan entity relation extraction based on multi-level attention fusion mechanism

Compared with Chinese and English, the training corpus of Tibetan entity relation is smaller, so it is difficult to obtain higher accuracy based on traditional supervised learning methods.And there exists the problem of wrong labels in distant supervision for relation extraction.To solve these probl...

Full description

Saved in:
Bibliographic Details
Main Authors: Like WANG, Yuan SUN, Sisi LIU
Format: Article
Language:zho
Published: POSTS&TELECOM PRESS Co., LTD 2021-12-01
Series:智能科学与技术学报
Subjects:
Online Access:http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202146
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850195646796005376
author Like WANG
Yuan SUN
Sisi LIU
author_facet Like WANG
Yuan SUN
Sisi LIU
author_sort Like WANG
collection DOAJ
description Compared with Chinese and English, the training corpus of Tibetan entity relation is smaller, so it is difficult to obtain higher accuracy based on traditional supervised learning methods.And there exists the problem of wrong labels in distant supervision for relation extraction.To solve these problems, the distant supervision method was used to construct the data set of Tibetan entity relation extraction through aligning the knowledge base with texts, which could alleviate the problem of lacking of large-scale corpus in Tibetan.And a Tibetan entity relation extraction model based on multi-level attention fusion mechanism was proposed.The self-attention was added to extract internal features of words in word level.The selective attention mechanism could assign weights of each instance, so as to make full use of informative sentences and reduce weights of noisy instances.Meanwhile, a joint score function was introduced to correct wrong labels, and neural network was combined with support vector machine to extract relations.Experimental results show that the proposed model can effectively improve the accuracy of Tibetan entity relation extraction, and is better than the baseline.
format Article
id doaj-art-103212d2e5ab4e079dd615abede35720
institution OA Journals
issn 2096-6652
language zho
publishDate 2021-12-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 智能科学与技术学报
spelling doaj-art-103212d2e5ab4e079dd615abede357202025-08-20T02:13:41ZzhoPOSTS&TELECOM PRESS Co., LTD智能科学与技术学报2096-66522021-12-01346647359641617Tibetan entity relation extraction based on multi-level attention fusion mechanismLike WANGYuan SUNSisi LIUCompared with Chinese and English, the training corpus of Tibetan entity relation is smaller, so it is difficult to obtain higher accuracy based on traditional supervised learning methods.And there exists the problem of wrong labels in distant supervision for relation extraction.To solve these problems, the distant supervision method was used to construct the data set of Tibetan entity relation extraction through aligning the knowledge base with texts, which could alleviate the problem of lacking of large-scale corpus in Tibetan.And a Tibetan entity relation extraction model based on multi-level attention fusion mechanism was proposed.The self-attention was added to extract internal features of words in word level.The selective attention mechanism could assign weights of each instance, so as to make full use of informative sentences and reduce weights of noisy instances.Meanwhile, a joint score function was introduced to correct wrong labels, and neural network was combined with support vector machine to extract relations.Experimental results show that the proposed model can effectively improve the accuracy of Tibetan entity relation extraction, and is better than the baseline.http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202146Tibetan;entity relation extraction;multi-level attention fusion mechanism;support vector machine
spellingShingle Like WANG
Yuan SUN
Sisi LIU
Tibetan entity relation extraction based on multi-level attention fusion mechanism
智能科学与技术学报
Tibetan;entity relation extraction;multi-level attention fusion mechanism;support vector machine
title Tibetan entity relation extraction based on multi-level attention fusion mechanism
title_full Tibetan entity relation extraction based on multi-level attention fusion mechanism
title_fullStr Tibetan entity relation extraction based on multi-level attention fusion mechanism
title_full_unstemmed Tibetan entity relation extraction based on multi-level attention fusion mechanism
title_short Tibetan entity relation extraction based on multi-level attention fusion mechanism
title_sort tibetan entity relation extraction based on multi level attention fusion mechanism
topic Tibetan;entity relation extraction;multi-level attention fusion mechanism;support vector machine
url http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202146
work_keys_str_mv AT likewang tibetanentityrelationextractionbasedonmultilevelattentionfusionmechanism
AT yuansun tibetanentityrelationextractionbasedonmultilevelattentionfusionmechanism
AT sisiliu tibetanentityrelationextractionbasedonmultilevelattentionfusionmechanism