UniTopRank : a scalable and language-independent method for toponym resolution
Xuke Hu, Yao Sun, Tobias Hecking, Jens Kersten, Friederike Klan
Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Toponym resolution is essential for extracting geographic information from unstructured texts. Although recent deep learning and large language model (LLM)–based methods achieve strong performance, they typically require substantial computational resources and have slow inference speeds, limiting their practicality for resource-constrained, large-scale or time-sensitive applications. Moreover, most existing approaches are developed for English or a limited set of languages, restricting their cross-lingual applicability. To fill the gaps, we propose UniTopRank, a universal, scalable, and language-independent method based on rule-driven ranking. It operates in two steps: first, candidate locations for all toponyms in a text are retrieved from gazetteers; second, the candidates are ranked using name similarity, population, administrative level, and spatial relationships among toponyms through beam search. We evaluate UniTopRank on 25 datasets in 14 languages and 7 text types, covering 186,100 toponyms worldwide. For 11 English datasets, we compare it with 21 existing methods, including deep learning– and LLM-based models, and for non-English datasets, with 12 representative approaches. Results show that UniTopRank attains accuracy comparable to state-of-the-art methods—though not the best—and generalizes well across different languages, while being significantly faster and much more resource-efficient. Running entirely on standard CPUs, it is well-suited for large-scale, multilingual, or resource-constrained applications.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
社会科学Geographic Information Systems Studies
Advanced Image and Video Retrieval Techniques · Memory, Trauma, and Commemoration
参考文献 43
此处列出前 3 条
引用本文 1
按被引量排序,此处列出前 3 条