ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917490385223680 |
|---|---|
| author | Higashiyama, Shohei Ouchi, Hiroki Fujita, Atsushi Utiyama, Masao |
| author_facet | Higashiyama, Shohei Ouchi, Hiroki Fujita, Atsushi Utiyama, Masao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_12933 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset Higashiyama, Shohei Ouchi, Hiroki Fujita, Atsushi Utiyama, Masao Computation and Language 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. |
| title | ATD-Trans: A Geographically Grounded Japanese-English Travelogue Translation Dataset |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.12933 |