Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation

TL;DR

This paper introduces a novel in-context learning method for low-resource Coptic-to-English translation, leveraging Universal Dependencies syntactic parses to improve translation accuracy.

Contribution

It combines dictionary-based glosses with syntactic analyses to enhance low-resource machine translation, setting new state-of-the-art results for Coptic.

Findings

Syntactic information alone is less effective than dictionary glosses.

Combining dictionary items with syntactic data yields significant translation improvements.

Achieves new state-of-the-art results for Coptic translation.

Abstract

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.