Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure

Semantic text similarity(STS) measure plays an important role in the practical application of natural language processing. However, due to the complexity of Chinese semantic comprehension and the lack of currently available Chinese text similarity datasets, present research on Chinese semantic text...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hao Zhang, HuaXiong Zhang, XingYu Lu, Qiang Gao
Formato:	article
Lenguaje:	EN
Publicado:	Tamkang University Press 2021
Materias:	chinese semantic textual similarity convolutional neural network attention mechanism aboen Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Physics QC1-999
Acceso en línea:	https://doaj.org/article/2b7ce13de19b41d1bf2936fce5aad52f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2b7ce13de19b41d1bf2936fce5aad52f
record_format	dspace
spelling	oai:doaj.org-article:2b7ce13de19b41d1bf2936fce5aad52f2021-11-23T16:46:01ZAttention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure10.6180/jase.202204_25(2).00052708-99672708-9975https://doaj.org/article/2b7ce13de19b41d1bf2936fce5aad52f2021-11-01T00:00:00Zhttp://jase.tku.edu.tw/articles/jase-202204-25-2-0005https://doaj.org/toc/2708-9967https://doaj.org/toc/2708-9975Semantic text similarity(STS) measure plays an important role in the practical application of natural language processing. However, due to the complexity of Chinese semantic comprehension and the lack of currently available Chinese text similarity datasets, present research on Chinese semantic text similarity still exists many limitations. In this paper, we construct a new private self-built Chinese semantic similarity (NCSS) dataset and propose a new method called Attention-based Overall Enhance Network (ABOEN) for measuring semantic textual similarity. This model takes advantage of a convolutional neural network upon soft attention layers to capture more fine-grained interactive features between two sentences. Besides, inspired by the channel attention mechanism in image classification, we adopt a channel attention mechanism to enhance the critical overall interactive features between two sentences. The experimental results show that compared with other baseline models, the accuracy based on our model on the NCSS and LCQMC datasets has increased by 1.38% and 1.49%, respectively, which proves the effectiveness of our proposed model.Hao ZhangHuaXiong ZhangXingYu LuQiang GaoTamkang University Pressarticlechinese semantic textual similarityconvolutional neural networkattention mechanismaboenEngineering (General). Civil engineering (General)TA1-2040Chemical engineeringTP155-156PhysicsQC1-999ENJournal of Applied Science and Engineering, Vol 25, Iss 2, Pp 287-295 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	chinese semantic textual similarity convolutional neural network attention mechanism aboen Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Physics QC1-999
spellingShingle	chinese semantic textual similarity convolutional neural network attention mechanism aboen Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Physics QC1-999 Hao Zhang HuaXiong Zhang XingYu Lu Qiang Gao Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure
description	Semantic text similarity(STS) measure plays an important role in the practical application of natural language processing. However, due to the complexity of Chinese semantic comprehension and the lack of currently available Chinese text similarity datasets, present research on Chinese semantic text similarity still exists many limitations. In this paper, we construct a new private self-built Chinese semantic similarity (NCSS) dataset and propose a new method called Attention-based Overall Enhance Network (ABOEN) for measuring semantic textual similarity. This model takes advantage of a convolutional neural network upon soft attention layers to capture more fine-grained interactive features between two sentences. Besides, inspired by the channel attention mechanism in image classification, we adopt a channel attention mechanism to enhance the critical overall interactive features between two sentences. The experimental results show that compared with other baseline models, the accuracy based on our model on the NCSS and LCQMC datasets has increased by 1.38% and 1.49%, respectively, which proves the effectiveness of our proposed model.
format	article
author	Hao Zhang HuaXiong Zhang XingYu Lu Qiang Gao
author_facet	Hao Zhang HuaXiong Zhang XingYu Lu Qiang Gao
author_sort	Hao Zhang
title	Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure
title_short	Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure
title_full	Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure
title_fullStr	Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure
title_full_unstemmed	Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure
title_sort	attention-based overall enhance network for chinese semantic textual similarity measure
publisher	Tamkang University Press
publishDate	2021
url	https://doaj.org/article/2b7ce13de19b41d1bf2936fce5aad52f
work_keys_str_mv	AT haozhang attentionbasedoverallenhancenetworkforchinesesemantictextualsimilaritymeasure AT huaxiongzhang attentionbasedoverallenhancenetworkforchinesesemantictextualsimilaritymeasure AT xingyulu attentionbasedoverallenhancenetworkforchinesesemantictextualsimilaritymeasure AT qianggao attentionbasedoverallenhancenetworkforchinesesemantictextualsimilaritymeasure
_version_	1718416200682176512

Attention-Based Overall Enhance Network for Chinese Semantic Textual Similarity Measure

Ejemplares similares