Abstract
Existing methods based on BERT are difficult to automatically identify and efficiently detect Chinese toponyms due to its irregularity and the intricate structure. To address this issue, this article introduces a novel toponym recognition model named EIBC, which is the abbreviation of ERNIE-Gram-IDCNN-BiLSTM-CRF. It consists of four parts: (1) ERNIE-Gram is selected for dynamic vector representations of toponyms and extracts toponym features; (2) the context features are dilated by IDCNN with different dilation scales; (3) BiLSTM is employed to capture bidirectional context information and to grasp a broader range of global context features, while removing the noise information through its gating mechanisms; and (4) it incorporates CRF for global optimization of toponym sequence labels, enhancing toponym recognition effectiveness. The proposed model is constructed based on a multi-layer deep learning framework by utilizing various advanced techniques to enhance the model's performance. Experimental results show that the EIBC model outperforms existing some state-of-the-art Chinese toponym recognition models.






Similar content being viewed by others
References
Alkouz B, Al Aghbari Z (2020) SNSJam: road traffic analysis and prediction by fusing data from multiple social networks. Inf Process Manage 57(1):102139
Al-Olimat HS, Thirunarayan K, Shalin V, Sheth A (2017) Location name extraction from targeted text streams using gazetteer-based statistical language models. Arxiv Preprint https://arxiv.org/abs/1708.03105
Andreadis S, Antzoulatos G, Mavropoulos T, Giannakeris P, Tzionis G, Pantelidis N, Ioannidis K, Karakostas A, Gialampoukidis I, Vrochidis S, Kompatsiaris I (2021) A social media analytics platform visualising the spread of COVID-19 in Italy via exploitation of automatically geotagged tweets. Online Soc Netw Med 23:100134. https://doi.org/10.1016/j.osnem.2021.100134
Basu M, Bit SD, Ghosh S (2022) Utilizing microblogs for optimized real-time resource allocation in post-disaster scenarios. Soc Netw Anal Min 12:1–20
Cui Y, Che W, Liu T, Qin B, Yang Z (2021) Pre-training with whole word masking for chinese bert. Trans Audio Speech Lang Process 29:3504–3514
De Bruijn JA, de Moel H, Jongman B, Wagemaker J, Aerts JC (2018) TAGGS: grouping tweets to improve global geoparsing for disaster response. J Geovis Spatial Anal 2(1):1–14
Giridhar P, Abdelzaher T, George J, Kaplan L (2015) On quality of event localization from social network feeds
Graves A, Schmidhuber JUR (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5–6):602–610
Gritta M, Pilehvar M, Collier N (2018) Which melbourne? Augmenting geocoding with maps
Hahmann S, Burghardt D (2013) How much information is geospatially referenced? Networks and cognition. Int J Geogr Inf Sci 27(6):1171–1189
Hu X, Sun Y, Zhou Z, Abdelzaher T, Kersten J, Klan F, Fan H, Wiegmann M (2022a) GazPNE2: a general place name extractor for microblogs fusing gazetteers and pretrained transformer models. IEEE Internet Things J 9(17):16259–16271
Hu X, Zhou Z, Li H, Hu Y, Gu F, Kersten J, Fan H, Klan F, Abdelzaher T (2022b) Location reference recognition from texts: a survey and comparison. Arxiv Preprint https://arxiv.org/abs/2207.01683
Joshi M, Chen D, Liu Y, Weld DS, Zettlemoyer L, Levy O (2020) Spanbert: improving pre-training by representing and predicting spans. Trans Assoc Comput Linguist 8:64–77
Karimzadeh M, Pezanowski S, MacEachren AM, Wallgr UN (2019) GeoTxt: a scalable geoparsing system for unstructured text geolocation. Trans GIS 23(1):118–136
Kumar A, Singh JP (2019) Location reference identification from tweets during emergencies: a deep learning approach. Int J Disaster Risk Reduct 33:365–375
Li L, Mao T, Huang D (2005) Extracting location names from Chinese texts based on SVM and KNN
Li N, Guan HM, Yang P, Dong WY (2020) Chinese named entity recognition method based on BERT-IDCNN-CRF. J Shan Dong Univ (science Edition) 55(1):102–109
Limsopatham N, Collier NH (2016) Bidirectional LSTM for named entity recognition in Twitter messages
Ma K, Tan Y, Xie Z, Qiu Q, Chen S (2022) Chinese toponym recognition with variant neural structures from social media messages based on BERT methods. J Geogr Syst 24(2):143–169. https://doi.org/10.1007/s10109-022-00375-9
Malmasi S, Dras M (2016) Location mention detection in tweets and microblogs
Murrieta-Flores P, Baron A, Gregory I, Hardie A, Rayson P (2015) Automatically analyzing large texts in a gis environment: the registrar general’s reports and cholera in the 19th century. Trans GIS 19(2):296–320
Ozdikis O, Ramampiaro H, Nørvåg K (2019) Locality-adapted kernel densities of term co-occurrences for location prediction of tweets. Inf Process Manage 56(4):1280–1299
Paradesi SM (2011) Geotagging tweets using their content
Santos R, Murrieta-Flores P, Calado PAV, Martins B (2018) Toponym matching through deep neural networks. Int J Geogr Inf Sci 32(2):324–348
Scheele C, Yu M, Huang Q (2021) Geographic context-aware text mining: enhance social media message classification for situational awareness by integrating spatial and temporal features. Int J Digital Earth 14(11):1721–1743
See L, Mooney P, Foody G, Bastin L, Comber A, Estima J, Fritz S, Kerle N, Jiang B, Laakso M (2016) Crowdsourcing, citizen science or volunteered geographic information? The current state of crowdsourced geographic information. ISPRS Int J Geo Inf 5(5):55
Shang L, Zhang Y, Youn C, Wang D (2022) SAT-Geo: a social sensing based content-only approach to geolocating abnormal traffic events using syntax-based probabilistic learning. Inf Process Manage 59(2):102807
Strubell E, Verga P, Belanger D, McCallum A (2017) Fast and accurate entity recognition with iterated dilated convolutions. Arxiv Preprint https://arxiv.org/abs/1702.02098
Suat-Rojas N, Gutierrez-Osorio C, Pedraza C (2022) Extraction and analysis of social networks data to detect traffic accidents. Information 13(1):26
Suwaileh R, Elsayed T, Imran M (2023) IDRISI-RE: a generalizable dataset with benchmarks for location mention recognition on disaster tweets. Inf Process Manage 60(3):103340
Suwaileh R, Elsayed T, Imran M, Sajjad H (2022) When a disaster happens, we are ready: location mention recognition from crisis tweets. Int J Disaster Risk Reduct 78:103107
Wang J, Hu Y, Joseph K (2020) NeuroTPR: a neuro-net toponym recognition model for extracting locations from social media messages. Trans GIS 24(3):719–735. https://doi.org/10.1111/tgis.12627
Wu L, Liu L, Li H (2017) Chinese place name recognition method based on conditional random field. Geomat Inf Sci Wuhan Univ 42(2):150–156
Xiao D, Li Y, Zhang H, Sun Y, Tian H, Wu H, Wang H (2020) Ernie-gram: pre-training with explicitly n-gram masked language modeling for natural language understanding. Arxiv Preprint https://arxiv.org/abs/2010.12148
Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. Arxiv Preprint https://arxiv.org/abs/1511.07122
Yu B, Wei J (2020) IDCNN-CRF-based domain named entity recognition method
Zhang H, Du Q, Chen Z, Zhang C (2022) A Chinese address parsing method using RoBERTa-BiLSTM-CRF. Geomat Inf Sci Wuhan Univ 47(5):665–672
Zhou B, Zou L, Mostafavi A, Lin B, Yang M, Gharaibeh N, Cai H, Abedin J, Mandal D (2022) VictimFinder: harvesting rescue requests in disaster response from social media with BERT. Comput Environ Urban Syst 95:101824
Zou L, Lam NS, Shams S, Cai H, Meyer MA, Yang S, Lee K, Park S, Reams MA (2019) Social and geographical disparities in Twitter use during Hurricane Harvey. Int J Digital Earth 12(11):1300–1318
Acknowledgements
This research was funded by the National Natural Science Foundation of China (41871320), the Key Science and Research Foundation of Education Department of Hunan Province of China (22A0341), the Science and Technology Innovation Program of Hunan Province (2023SK2081), and the Hunan Provincial Natural Science Foundation of China (2021JJ30276).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, Y., Zhang, D., Jiang, L. et al. EIBC: a deep learning framework for Chinese toponym recognition with multiple layers. J Geogr Syst 26, 407–425 (2024). https://doi.org/10.1007/s10109-024-00441-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10109-024-00441-4