ATD-Trans: 一种地理导向的日英旅行日志翻译数据集
ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset
AI总结：
本文提出ATD-Trans数据集，用于评估机器翻译在地理实体层面的性能，探讨模型语言倾向和地理区域对翻译质量的影响。
摘要：
地理文本，即富含地理（geo-）信息的文本数据，是各种地理应用的重要资源，例如旅游业管理。使此类信息对其他语言的使用者可访问，进一步增强了其用途；因此，准确的机器翻译（MT）对于多语言地理信息访问的公平性至关重要。为了促进对地理文本的深入分析，我们介绍了ATD-Trans，一个地理导向的日英旅行日志翻译数据集，该数据集能够在国内外地区层面评估MT质量。我们对现有语言模型进行实验，检验两个因素：模型语言倾向和地理区域。结果突显了日语增强模型的优势，并指出在旅行博客中提及的国内地区地理实体翻译更具挑战性。
英文摘要：
Geographic text, or textual data rich in geographic (geo-) information is a valuable source for various geographic applications, e.g., tourism management. Making such information accessible to speakers of other languages further enhances its utility; thus, accurate machine translation (MT) is essential for equity in multilingual geo-information access. To facilitate in-depth analysis for geographic text, we introduce ATD-Trans, a geographically grounded Japanese--English travelogue translation dataset, which enables evaluation of MT quality at both the overall and geo-entity levels across domestic (within Japan) and overseas regions. Our experiments on existing language models examine two factors: model language focus and geographic regions. The results highlight advantages of Japanese-enhanced models and greater difficulty in translating domestic-region geo-entities mentioned in travel blogs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
