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

arXiv cs.CL Papers

Summary

This paper presents the development of Cantonese and Irish treebanks within the ParGram Project and investigates the potential and limitations of using multilingual LLMs (OpenAI's gpt-oss-120b) for grammar engineering tasks such as translation and syntactic structure generation.

arXiv:2608.07283v1 Announce Type: new Abstract: Grammar engineering requires expertise in linguistic formalism and computational implementation, especially 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 investigate 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 model. The results show 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.
Original Article
View Cached Full Text

Cached at: 08/10/26, 08:05 AM

# Grammar Engineering Meets LLMs: Development of Cantonese and Irish ParGram Treebanks
Source: [https://arxiv.org/abs/2608.07283](https://arxiv.org/abs/2608.07283)
[View PDF](https://arxiv.org/pdf/2608.07283)

> Abstract:Grammar engineering requires expertise in linguistic formalism and computational implementation, especially 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 investigate 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 model\. The results show 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\.

## Submission history

From: Elaine Uí Dhonnchadha \[[view email](https://arxiv.org/show-email/c3e83368/2608.07283)\] **\[v1\]**Fri, 7 Aug 2026 14:44:19 UTC \(729 KB\)

Similar Articles

LLMs for automatic annotation of Mandarin narrative transcripts

arXiv cs.CL

This paper evaluates LLMs for automatically annotating narrative macrostructure in spoken Mandarin, finding that the best model achieves near-human reliability while reducing annotation time by 65%, though performance degrades on semantically complex or lexically diverse narratives.