ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset
For researchers in machine translation and geographic information access, this dataset enables fine-grained evaluation of geo-entity translation, though the findings are incremental.
The paper introduces ATD-Trans, a Japanese-English travelogue translation dataset with geographic grounding, and evaluates MT models, finding that Japanese-enhanced models perform better and domestic geo-entities are harder to translate.
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.