中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network

文献类型：期刊论文

作者Qiu, Qinjun3,4,5; Xie, Zhong3,4; Wang, Shu1; Zhu, Yunqiang1,6; Lv, Hairong2; Sun, Kai1
刊名TRANSACTIONS IN GIS
出版日期2022-02-02
页码24
ISSN号1361-1682
DOI10.1111/tgis.12902
通讯作者Wang, Shu(wangshu@igsnrr.ac.cn)
英文摘要Toponym recognition is used to extract toponyms from natural language texts, which is a fundamental task of ubiquitous geographic information applications. Existing toponym recognition methods with state-of-the-art performance mainly leverage supervised learning (i.e., deep-learning-based approaches) with parameters learned from massive, labeled datasets that must be annotated manually. This is a great inconvenience when model training needs to fit different domain texts, especially those of social media messaging. To address this issue, this article proposes a weakly supervised Chinese toponym recognition (ChineseTR) architecture that leverages a training dataset creator that generates training datasets automatically based on word collections and associated word frequencies from various texts and an extension recognizer that employs a basic bidirectional recurrent neural network based on particular features designed for toponym recognition. The results show that the proposed ChineseTR achieves a 0.76 F1 score in a corpus with a 0.718 out-of-vocabulary rate and a 0.903 in-vocabulary rate. All comparative experiments demonstrate that ChineseTR is an effective and scalable architecture that recognizes toponyms.
WOS关键词GEOGRAPHIC ENVIRONMENTS VGES ; CLASSIFICATION
资助项目National Natural Science Foundation of China[42050101] ; National Natural Science Foundation of China[U1711267] ; National Natural Science Foundation of China[41871311] ; National Natural Science Foundation of China[41871305] ; National Natural Science Foundation of China[42101467] ; Hubei Key Laboratory of Intelligent Geo-Information Processing[KLIGIP-2021A01] ; China Postdoctoral Science Foundation[2021M702991] ; Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan)[CUG2106116]
WOS研究方向Geography
语种英语
WOS记录号WOS:000749899900001
出版者WILEY
资助机构National Natural Science Foundation of China ; Hubei Key Laboratory of Intelligent Geo-Information Processing ; China Postdoctoral Science Foundation ; Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan)
源URL[http://ir.igsnrr.ac.cn/handle/311030/170280]  
专题中国科学院地理科学与资源研究所
通讯作者Wang, Shu
作者单位1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China
2.Tsinghua Univ, Dept Automat, Beijing, Peoples R China
3.Natl Engn Res Ctr Geog Informat Syst, Wuhan, Peoples R China
4.China Univ Geosci, Sch Geog & Informat Engn, Wuhan, Peoples R China
5.China Univ Geosci, Hubei Key Lab Intelligent Geoinformat Proc, Wuhan, Peoples R China
6.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing, Peoples R China
推荐引用方式
GB/T 7714		 Qiu, Qinjun,Xie, Zhong,Wang, Shu,et al. ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network[J]. TRANSACTIONS IN GIS,2022:24.
APA Qiu, Qinjun,Xie, Zhong,Wang, Shu,Zhu, Yunqiang,Lv, Hairong,&Sun, Kai.(2022).ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network.TRANSACTIONS IN GIS,24.
MLA Qiu, Qinjun,et al."ChineseTR: A weakly supervised toponym recognition architecture based on automatic training data generator and deep neural network".TRANSACTIONS IN GIS (2022):24.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。