How can voting mechanisms improve the robustness and generalizability of toponym disambiguation?

Xuke Hu, Yeran Sun, J. Kersten, Zhiyong Zhou, Friederike Klan, H. Fan
{"title":"How can voting mechanisms improve the robustness and generalizability of toponym disambiguation?","authors":"Xuke Hu, Yeran Sun, J. Kersten, Zhiyong Zhou, Friederike Klan, H. Fan","doi":"10.48550/arXiv.2209.08286","DOIUrl":null,"url":null,"abstract":"A vast amount of geographic information exists in natural language texts, such as tweets and news. Extracting geographic information from texts is called Geoparsing, which includes two subtasks: toponym recognition and toponym disambiguation, i.e., to identify the geospatial representations of toponyms. This paper focuses on toponym disambiguation, which is usually approached by toponym resolution and entity linking. Recently, many novel approaches have been proposed, especially deep learning-based approaches, such as CamCoder, GENRE, and BLINK. In this paper, a spatial clustering-based voting approach that combines several individual approaches is proposed to improve SOTA performance in terms of robustness and generalizability. Experiments are conducted to compare a voting ensemble with 20 latest and commonly-used approaches based on 12 public datasets, including several highly ambiguous and challenging datasets (e.g., WikToR and CLDW). The datasets are of six types: tweets, historical documents, news, web pages, scientific articles, and Wikipedia articles, containing in total 98,300 places across the world. The results show that the voting ensemble performs the best on all the datasets, achieving an average Accuracy@161km of 0.86, proving the generalizability and robustness of the voting approach. Also, the voting ensemble drastically improves the performance of resolving fine-grained places, i.e., POIs, natural features, and traffic ways.","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Appl. Earth Obs. Geoinformation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2209.08286","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

A vast amount of geographic information exists in natural language texts, such as tweets and news. Extracting geographic information from texts is called Geoparsing, which includes two subtasks: toponym recognition and toponym disambiguation, i.e., to identify the geospatial representations of toponyms. This paper focuses on toponym disambiguation, which is usually approached by toponym resolution and entity linking. Recently, many novel approaches have been proposed, especially deep learning-based approaches, such as CamCoder, GENRE, and BLINK. In this paper, a spatial clustering-based voting approach that combines several individual approaches is proposed to improve SOTA performance in terms of robustness and generalizability. Experiments are conducted to compare a voting ensemble with 20 latest and commonly-used approaches based on 12 public datasets, including several highly ambiguous and challenging datasets (e.g., WikToR and CLDW). The datasets are of six types: tweets, historical documents, news, web pages, scientific articles, and Wikipedia articles, containing in total 98,300 places across the world. The results show that the voting ensemble performs the best on all the datasets, achieving an average Accuracy@161km of 0.86, proving the generalizability and robustness of the voting approach. Also, the voting ensemble drastically improves the performance of resolving fine-grained places, i.e., POIs, natural features, and traffic ways.
投票机制如何提高地名消歧的鲁棒性和泛化性?
大量的地理信息存在于自然语言文本中,如推文和新闻。从文本中提取地理信息称为地理解析,它包括两个子任务:地名识别和地名消歧,即识别地名的地理空间表示。本文主要研究地名消歧问题,通常采用地名解析和实体链接的方法。最近,人们提出了许多新颖的方法,特别是基于深度学习的方法,如CamCoder、GENRE和BLINK。本文提出了一种基于空间聚类的投票方法,该方法结合了几种单独的方法,以提高SOTA的鲁棒性和泛化性。实验将投票集成与基于12个公共数据集的20种最新常用方法进行比较,包括几个高度模糊和具有挑战性的数据集(例如,WikToR和CLDW)。这些数据集有六种类型:推文、历史文档、新闻、网页、科学文章和维基百科文章,总共包含世界各地的98,300个地方。结果表明,投票集合在所有数据集上的表现最好,平均得分Accuracy@161km为0.86,证明了投票方法的可泛化性和鲁棒性。此外,投票集成极大地提高了解析细粒度位置(即poi、自然特征和交通方式)的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信