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

2026-04-20 · Source: Computation and Language · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Expert, quick

Summary

A new in-context learning method enhances low-resource machine translation for Coptic to English by integrating syntactic augmentation from Universal Dependencies (UD) parses. This approach builds on existing bilingual dictionary-based inference by adding various syntactic representations to model inputs, including raw parser outputs, plain English verbalizations of parses, and targeted instructions for difficult constructions. While syntactic information alone is less effective than dictionary glosses, its combination with retrieved dictionary items yields substantial improvements across different model sizes, establishing new state-of-the-art translation results for Coptic. This research addresses the challenges of translating languages with limited data resources.

Key takeaway

For research scientists developing machine translation systems for low-resource languages, you should explore integrating Universal Dependencies syntactic parses with existing dictionary-based glosses. This combined approach has demonstrated significant performance gains for Coptic, suggesting a robust strategy for improving translation quality where data is scarce.

Key insights

Syntactic augmentation via Universal Dependencies significantly improves low-resource Coptic-to-English machine translation when combined with dictionary glosses.

Principles

• Low-resource MT needs specialized methods.
• Syntactic data complements lexical glosses.

Method

The method augments in-context learning for Coptic-to-English MT by integrating Universal Dependencies parses (raw, verbalized, and targeted instructions) with retrieved bilingual dictionary items into the input.

In practice

• Combine syntactic data with lexical glosses.
• Use UD parses for low-resource MT.

Topics

• Low-resource Machine Translation
• Coptic Language
• Universal Dependencies
• In-context Learning
• Syntactic Augmentation

Best for: Research Scientist, AI Scientist, NLP Engineer

Related on AIssential

• Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation — Syntactic augmentation, combined with lexical information, significantly boosts low-resource machine translation quality.
• AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages — AfriSUD provides the first large-scale, native-speaker verified dependency treebanks for nine diverse African languages, revealing a significant syntax gap in current NLP models.
• A UD Parser to the Rescue: A Method for Bringing a Classical Annotated Corpus to Life Again — A knowledge-rich parsing method can effectively update classical linguistic corpora to modern annotation standards.
• AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents — Glossary-augmented LLMs significantly improve terminology accuracy in specialized translation without sacrificing overall quality.
• Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages — Biaffine LSTMs excel in low-resource dependency parsing, outperforming Transformers until sufficient data is available.
• Universal Dependencies v2.5 Benchmarks for spaCy — spaCy v3.2 demonstrates competitive performance against Stanza and Trankit on Universal Dependencies v2.5 benchmarks using CoNLL 2018 evaluation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computation and Language.