Enhancing Chinese Address Parsing in Low-Resource Scenarios through In-Context Learning

Author:

Ling Guangming1ORCID,Mu Xiaofeng12,Wang Chao3ORCID,Xu Aiping1

Affiliation:

1. School of Computer Science, Wuhan University, Wuhan 430072, China

2. Wuhan Children’s Hospital (Wuhan Maternal and Child Healthcare Hospital), Tongji Medical College, Huazhong University of Science & Technology, Wuhan 430074, China

3. The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430072, China

Abstract

Address parsing is a crucial task in natural language processing, particularly for Chinese addresses. The complex structure and semantic features of Chinese addresses present challenges due to their inherent ambiguity. Additionally, different task scenarios require varying levels of granularity in address components, further complicating the parsing process. To address these challenges and adapt to low-resource environments, we propose CapICL, a novel Chinese address parsing model based on the In-Context Learning (ICL) framework. CapICL leverages a sequence generator, regular expression matching, BERT semantic similarity computation, and Generative Pre-trained Transformer (GPT) modeling to enhance parsing accuracy by incorporating contextual information. We construct the sequence generator using a small annotated dataset, capturing distribution patterns and boundary features of address types to model address structure and semantics, which mitigates interference from unnecessary variations. We introduce the REB–KNN algorithm, which selects similar samples for ICL-based parsing using regular expression matching and BERT semantic similarity computation. The selected samples, raw text, and explanatory text are combined to form prompts and inputted into the GPT model for prediction and address parsing. Experimental results demonstrate significant achievements of CapICL in low-resource environments, reducing dependency on annotated data and computational resources. Our model’s effectiveness, adaptability, and broad application potential are validated, showcasing its positive impact in natural language processing and geographical information systems.

Funder

National Key R&D Program of China

Key R&D Program of Hubei Province

National Natural Science Foundation of China program

Open Fund of National Engineering Research Centre for Geographic Information System

Publisher

MDPI AG

Subject

Earth and Planetary Sciences (miscellaneous),Computers in Earth Sciences,Geography, Planning and Development

Reference36 articles.

1. NeuroTPR: A Neuro-net Toponym Recognition Model for Extracting Locations from Social Media Messages;Wang;Trans. GIS,2020

2. Tao, L., Xie, Z., Xu, D., Ma, K., Qiu, Q., Pan, S., and Huang, B. (2022). Geographic Named Entity Recognition by Employing Natural Language Processing and an Improved BERT Model. ISPRS Int. J. Geo-Inf., 11.

3. Context-Aware Automated Interpretation of Elaborate Natural Language Descriptions of Location through Learning from Empirical Data;Stock;Int. J. Geogr. Inf. Sci.,2018

4. Transformer Based Named Entity Recognition for Place Name Extraction from Unstructured Text;Berragan;Int. J. Geogr. Inf. Sci.,2023

5. Li, H., Lu, W., Xie, P., and Li, L. (2019, January 2–7). Neural Chinese Address Parsing. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3