Grammar Engineering Meets LLMs: Development of Cantonese and Irish ParGram Treebanks

Researchers Chit-Fung Lam and Elaine Uí Dhonnchadha presented the development of Cantonese and Irish treebanks within the Parallel Grammar (ParGram) Project at the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics (BriGap-3) in Paris, France, in July 2026. Testing OpenAI's gpt-oss-120b for Cantonese–Irish translation and syntactic structure generation, they found translation performance generally unsatisfactory and unaffected by prompt language, while structure generation produced some meaningful outputs but failed on cross-linguistic abstraction, underscoring the continued need for expert-driven analysis.

Abstract Grammar engineering requires expertise in linguistic formalism and computational implementation, particularly in parallel grammar projects that balance cross-linguistic consistency with language-specific properties. This paper presents the development of Cantonese and Irish treebanks within the Parallel Grammar ParGram Project, where linguistic parallelism is maintained at an abstract functional level. We also investigated the methodological potential and limitations of using multilingual LLMs to support grammar engineering, focusing on Cantonese–Irish translation and the generation of formal syntactic structures using OpenAI’s gpt-oss-120b. The results showed that translation performance was generally unsatisfactory and unaffected by prompt language. For syntactic structure generation, the model produced some structurally meaningful outputs, but performed poorly on tasks requiring cross-linguistic abstraction. Nonetheless, LLM-generated outputs may still offer some reference value by suggesting alternative analyses and partially capturing predicate–argument relations. Overall, our findings highlight both the potential and limitations of using LLMs in collaborative grammar engineering, while underscoring the continued importance of expert-driven analysis and verification.- Anthology ID: - 2026.brigap-1.11 - Volume: Proceedings of the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics BriGap-3 /volumes/2026.brigap-1/ - Month: - July - Year: - 2026 - Address: - Paris, France - Editors: Timothée Bernard /people/timothee-bernard/ , Emmanuele Chersoni /people/emmanuele-chersoni/ , Giulia Rambelli /people/giulia-rambelli/unverified/ - Venues: BriGap /venues/brigap/ | WS /venues/ws/ - SIG: - Publisher: - Association for Computational Linguistics - Note: - Pages: - 121–134 - Language: - URL: https://aclanthology.org/2026.brigap-1.11/ https://aclanthology.org/2026.brigap-1.11/ - DOI: - Cite ACL : - Chit-Fung Lam and Elaine Uí Dhonnchadha. 2026. Grammar Engineering Meets LLMs: Development of Cantonese and Irish ParGram Treebanks https://aclanthology.org/2026.brigap-1.11/ . In Proceedings of the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics BriGap-3 , pages 121–134, Paris, France. Association for Computational Linguistics. - Cite Informal : Grammar Engineering Meets LLMs: Development of Cantonese and Irish ParGram Treebanks https://aclanthology.org/2026.brigap-1.11/ Lam & Uí Dhonnchadha, BriGap 2026 - PDF: https://aclanthology.org/2026.brigap-1.11.pdf https://aclanthology.org/2026.brigap-1.11.pdf