Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a novel in-context learning approach for low-resource Coptic-to-English machine translation by augmenting input sentences with Universal Dependencies parses. They explore raw parser outputs, verbalizations of parses, and targeted instructions for difficult syntactic constructions, combining these with dictionary-based glosses. Results demonstrate that syntactic information, when combined with dictionary items, significantly improves translation performance, establishing a new state-of-the-art for Coptic translation.
Injecting syntactic structure into in-context learning unlocks surprisingly large gains in low-resource machine translation, even when syntax alone falls short.
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.