Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network
Spatial entity descriptions are written in natural language based on the observations and understanding of spatial entities and often contain rich semantic information beyond GIS systems. Therefore, entity descriptions must be related to spatial entities in GIS systems. However, most previous studie...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8360429/ |
id |
doaj-8d540065ef754b1c87ecbe9de93bd3bd |
---|---|
record_format |
Article |
spelling |
doaj-8d540065ef754b1c87ecbe9de93bd3bd2021-03-29T20:50:10ZengIEEEIEEE Access2169-35362018-01-016280642807210.1109/ACCESS.2018.28376668360429Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention NetworkKai Ma0https://orcid.org/0000-0003-2827-767XLiang Wu1Liufeng Tao2Wenjia Li3Zhong Xie4Department of Information Engineering, China University of Geosciences, Wuhan, ChinaDepartment of Information Engineering, China University of Geosciences, Wuhan, ChinaDepartment of Information Engineering, China University of Geosciences, Wuhan, ChinaDepartment of Information Engineering, China University of Geosciences, Wuhan, ChinaDepartment of Information Engineering, China University of Geosciences, Wuhan, ChinaSpatial entity descriptions are written in natural language based on the observations and understanding of spatial entities and often contain rich semantic information beyond GIS systems. Therefore, entity descriptions must be related to spatial entities in GIS systems. However, most previous studies of this issue were confined to place-type spatial entities, and other types of instance-level spatial entity matching have rarely been studied. In addition, existing matching methods require complex semantic analysis and manual feature engineering for the description text. In this paper, we focus on the matching of semantic similarity between spatial entities with rich text attributes and descriptions. We propose a semantic textual similarity matching model that incorporates a hierarchical recurrent structure with a focus on learning low-dimensional semantic vector representations of spatial entities and the corresponding descriptions. The model minimizes the distance between the vectors of matched pairs and maximizes the distance between the mismatched pairs of samples. The proposed siamese hierarchical attention network is trained and evaluated using a geological survey data set. The results show that the proposed model effectively captures the salient semantic information of spatial entities and the associated descriptions in the matching task and significantly outperforms previous state-of-the-art matching models.https://ieeexplore.ieee.org/document/8360429/Semantic representationsimilarity matchingspatial entityspatial entity description |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kai Ma Liang Wu Liufeng Tao Wenjia Li Zhong Xie |
spellingShingle |
Kai Ma Liang Wu Liufeng Tao Wenjia Li Zhong Xie Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network IEEE Access Semantic representation similarity matching spatial entity spatial entity description |
author_facet |
Kai Ma Liang Wu Liufeng Tao Wenjia Li Zhong Xie |
author_sort |
Kai Ma |
title |
Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network |
title_short |
Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network |
title_full |
Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network |
title_fullStr |
Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network |
title_full_unstemmed |
Matching Descriptions to Spatial Entities Using a Siamese Hierarchical Attention Network |
title_sort |
matching descriptions to spatial entities using a siamese hierarchical attention network |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Spatial entity descriptions are written in natural language based on the observations and understanding of spatial entities and often contain rich semantic information beyond GIS systems. Therefore, entity descriptions must be related to spatial entities in GIS systems. However, most previous studies of this issue were confined to place-type spatial entities, and other types of instance-level spatial entity matching have rarely been studied. In addition, existing matching methods require complex semantic analysis and manual feature engineering for the description text. In this paper, we focus on the matching of semantic similarity between spatial entities with rich text attributes and descriptions. We propose a semantic textual similarity matching model that incorporates a hierarchical recurrent structure with a focus on learning low-dimensional semantic vector representations of spatial entities and the corresponding descriptions. The model minimizes the distance between the vectors of matched pairs and maximizes the distance between the mismatched pairs of samples. The proposed siamese hierarchical attention network is trained and evaluated using a geological survey data set. The results show that the proposed model effectively captures the salient semantic information of spatial entities and the associated descriptions in the matching task and significantly outperforms previous state-of-the-art matching models. |
topic |
Semantic representation similarity matching spatial entity spatial entity description |
url |
https://ieeexplore.ieee.org/document/8360429/ |
work_keys_str_mv |
AT kaima matchingdescriptionstospatialentitiesusingasiamesehierarchicalattentionnetwork AT liangwu matchingdescriptionstospatialentitiesusingasiamesehierarchicalattentionnetwork AT liufengtao matchingdescriptionstospatialentitiesusingasiamesehierarchicalattentionnetwork AT wenjiali matchingdescriptionstospatialentitiesusingasiamesehierarchicalattentionnetwork AT zhongxie matchingdescriptionstospatialentitiesusingasiamesehierarchicalattentionnetwork |
_version_ |
1724194063204220928 |