构建俄鞑双语地名数据集，提升多语言地理问答准确率
Tatarstan Toponyms: A Bilingual Dataset and Hybrid RAG System for Geospatial Question Answering
- 混合检索：融合语义向量与空间距离，精准定位地名
- 测试集上召回率98.8%，答案精确率达99.2%以上
- 适合地理信息、数字人文及多语言系统开发者使用
本文针对多语言地名数据的端到端地理问答问题，构建了包含9,688个地名的俄语-鞑靼语双语数据集，涵盖语言学、词源和坐标信息，93.1%的地名已地理标注。基于此构建约39,000个带上下文与答案的问答对，确保答案可精确定位。系统采用混合检索器（multilingual-e5-large语义索引+基于KD树与哈弗辛距离的空间过滤/排序）与微调过的抽取式阅读器（RuBERT、XLM-RoBERTa-large、T5-RUS）。在500个测试查询中，混合检索达到Recall@1=0.988，Recall@5=1.000，MRR=0.994，显著优于BM25和仅空间方法。其中XLM-RoBERTa-large表现最佳：EM=0.992，F1=0.994。RuBERT在坐标类问题上因分词缺陷失败，但经简单后处理可恢复100%准确率。资源（数据集、问答语料、模型、网页演示）已公开发布于Hugging Face。成果可直接应用于地理问答服务、地理编码与数字人文项目。
原文摘要 · Abstract (English)
This paper addresses end-to-end geospatial question answering over multilingual toponymic data. We introduce a bilingual (Russian-Tatar) dataset of 9,688 toponyms with linguistic, etymological, and coordinate information (93.1 percent georeferenced). Based on this, we construct about 39,000 question-context-answer triples with guaranteed answer localization. Our architecture combines a hybrid retriever (dense semantic indexing with multilingual-e5-large plus geospatial filtering/ranking using KD-trees and haversine distance) and an extractive reader fine-tuned on transformer models. On 500 test queries, hybrid search achieves Recall@1 = 0.988, Recall@5 = 1.000, MRR = 0.994, significantly outperforming BM25 and spatial-only methods. Among readers (RuBERT, XLM-RoBERTa-large, T5-RUS), XLM-RoBERTa-large gives best results: EM = 0.992, F1 = 0.994. RuBERT models fail on coordinate questions due to tokenization artifacts, but simple post-processing recovers 100 percent accuracy. Resources (dataset, QA corpus, models, web demo) are openly released on Hugging Face. Results are directly applicable to geospatial QA services, geocoding, and digital humanities projects.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。