cd /news/large-language-models/grammar-engineering-meets-llms-devel… · home topics large-language-models article
[ARTICLE · art-86801] src=aclanthology.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

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.

read1 min views13 publishedJul 31, 2026
Grammar Engineering Meets LLMs: Development of Cantonese and Irish ParGram Treebanks
Image: Aclanthology (auto-discovered)
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):
[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)
── more in #large-language-models 4 stories · sorted by recency
── more on @chit-fung lam 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/grammar-engineering-…] indexed:0 read:1min 2026-07-31 ·