Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation
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_ | 1866916051874217984 |
|---|---|
| author | Purushothama, Abhishek Thronson, Emma Guo, Alexia Zeldes, Amir |
| author_facet | Purushothama, Abhishek Thronson, Emma Guo, Alexia Zeldes, Amir |
| contents | Low-resource machine translation requires methods that differ from those used for high-resource languages. This paper proposes a novel in-context learning approach to support low-resource machine translation of the Coptic language to English, with syntactic augmentation from Universal Dependencies parses of input sentences. Building on existing work using bilingual dictionaries to support inference for vocabulary items, we add several representations of syntactic analyses to our inputs , specifically exploring the inclusion of raw parser outputs, verbalizations of parses in plain English, and targeted instructions of difficult constructions identified in sub-trees and how they can be translated. Our results show that while syntactic information alone is not as useful as dictionary-based glosses, combining retrieved dictionary items with syntactic information achieves significant gains across model sizes, achieving new state-of-the-art translation results for Coptic. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18758 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation Purushothama, Abhishek Thronson, Emma Guo, Alexia Zeldes, Amir Computation and Language Low-resource machine translation requires methods that differ from those used for high-resource languages. This paper proposes a novel in-context learning approach to support low-resource machine translation of the Coptic language to English, with syntactic augmentation from Universal Dependencies parses of input sentences. Building on existing work using bilingual dictionaries to support inference for vocabulary items, we add several representations of syntactic analyses to our inputs , specifically exploring the inclusion of raw parser outputs, verbalizations of parses in plain English, and targeted instructions of difficult constructions identified in sub-trees and how they can be translated. Our results show that while syntactic information alone is not as useful as dictionary-based glosses, combining retrieved dictionary items with syntactic information achieves significant gains across model sizes, achieving new state-of-the-art translation results for Coptic. |
| title | Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.18758 |