Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.

Automatic generation of entity synonyms plays a pivotal role in various natural language processing applications, such as search engines, question-answering systems, and taxonomy construction. Previous research on generating entity synonym sets has typically relied on approaches that involve sorting...

Full description

Saved in:
Bibliographic Details
Main Authors: Subin Huang, Daoyu Li, Chengzhen Yu, Junjie Chen, Qing Zhou, Sanmin Liu
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0321381
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711392545832960
author Subin Huang
Daoyu Li
Chengzhen Yu
Junjie Chen
Qing Zhou
Sanmin Liu
author_facet Subin Huang
Daoyu Li
Chengzhen Yu
Junjie Chen
Qing Zhou
Sanmin Liu
author_sort Subin Huang
collection DOAJ
description Automatic generation of entity synonyms plays a pivotal role in various natural language processing applications, such as search engines, question-answering systems, and taxonomy construction. Previous research on generating entity synonym sets has typically relied on approaches that involve sorting and pruning candidate entities or solving the problem in a two-stage manner (i.e., initially identifying pairs of synonyms and subsequently aggregating them into sets). Nevertheless, these approaches tend to disregard global entity information and are susceptible to error propagation issues. This paper introduces an innovative approach to generating entity synonym sets that leverages a flexible perception mechanism and multi-layer contextual information. Firstly, to determine whether to incorporate new candidate entities into synonym sets, the approach integrates a neural network classifier with a flexible perceptual field. Within the classifier, the approach builds a three-layer interactive network, and connects the entity layer, set layer, and sentence layer to the same embedding space to extract synonym features. Secondly, we introduce a dynamic-weight-based algorithm for synthesizing entity synonym sets, leveraging a neural network classifier trained to generate entity synonym sets from the candidate entity vocabulary. Finally, extensive experimental results on three public datasets demonstrate that our approach outperforms other comparable approaches in generating entity synonym sets.
format Article
id doaj-art-169416f7fca8493d8c340fe6d6d2012a
institution DOAJ
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-169416f7fca8493d8c340fe6d6d2012a2025-08-20T03:14:38ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01204e032138110.1371/journal.pone.0321381Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.Subin HuangDaoyu LiChengzhen YuJunjie ChenQing ZhouSanmin LiuAutomatic generation of entity synonyms plays a pivotal role in various natural language processing applications, such as search engines, question-answering systems, and taxonomy construction. Previous research on generating entity synonym sets has typically relied on approaches that involve sorting and pruning candidate entities or solving the problem in a two-stage manner (i.e., initially identifying pairs of synonyms and subsequently aggregating them into sets). Nevertheless, these approaches tend to disregard global entity information and are susceptible to error propagation issues. This paper introduces an innovative approach to generating entity synonym sets that leverages a flexible perception mechanism and multi-layer contextual information. Firstly, to determine whether to incorporate new candidate entities into synonym sets, the approach integrates a neural network classifier with a flexible perceptual field. Within the classifier, the approach builds a three-layer interactive network, and connects the entity layer, set layer, and sentence layer to the same embedding space to extract synonym features. Secondly, we introduce a dynamic-weight-based algorithm for synthesizing entity synonym sets, leveraging a neural network classifier trained to generate entity synonym sets from the candidate entity vocabulary. Finally, extensive experimental results on three public datasets demonstrate that our approach outperforms other comparable approaches in generating entity synonym sets.https://doi.org/10.1371/journal.pone.0321381
spellingShingle Subin Huang
Daoyu Li
Chengzhen Yu
Junjie Chen
Qing Zhou
Sanmin Liu
Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.
PLoS ONE
title Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.
title_full Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.
title_fullStr Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.
title_full_unstemmed Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.
title_short Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information.
title_sort empowering entity synonym set generation using flexible perceptual field and multi layer contextual information
url https://doi.org/10.1371/journal.pone.0321381
work_keys_str_mv AT subinhuang empoweringentitysynonymsetgenerationusingflexibleperceptualfieldandmultilayercontextualinformation
AT daoyuli empoweringentitysynonymsetgenerationusingflexibleperceptualfieldandmultilayercontextualinformation
AT chengzhenyu empoweringentitysynonymsetgenerationusingflexibleperceptualfieldandmultilayercontextualinformation
AT junjiechen empoweringentitysynonymsetgenerationusingflexibleperceptualfieldandmultilayercontextualinformation
AT qingzhou empoweringentitysynonymsetgenerationusingflexibleperceptualfieldandmultilayercontextualinformation
AT sanminliu empoweringentitysynonymsetgenerationusingflexibleperceptualfieldandmultilayercontextualinformation