cd /news/machine-learning/automated-information-extraction-and… · home › topics › machine-learning › article
[ARTICLE · art-115236] src=aclanthology.org ↗ pub= topic=machine-learning verified=true sentiment=· neutral

Automated Information Extraction and Template Filling from Client Style Guides

Researchers Leonor Graça, Vera Cabarrão, and Helena Moniz presented exploratory work at the 26th Annual Conference of the European Association for Machine Translation (EAMT) on automatically extracting information from client style guides and filling a templated style guide used as a system prompt for LLM-based translation. Evaluating seven language pairs, they found reliable extraction performance and, via human preference annotation, a modest advantage for the Tower+ 72B model over Tower Zen 9B in translation quality and compliance, establishing a viable semi-automatic framework for style guide integration.

read2 min views23 publishedAug 24, 2026
Automated Information Extraction and Template Filling from Client Style Guides
Image: Aclanthology (auto-discovered)
Abstract

Style guides are a centrepiece of professional translation workflows. Yet, their integration into automatic pipelines remains underexplored. This paper presents exploratory work on information extraction from client style guides and application to a templated style guide, developed to be a system prompt. This template is then applied during an LLM-based translation to automatically produce outputs that are compliant to client’s requirements. The study focused on seven language pairs~(LP), evaluating the automatic extraction, and translation quality and compliance with the style guide. The extraction demonstrated reliable performance across languages and file formats. Translation quality and adherence were evaluated using human preference annotation, comparing two Tower models (Tower Zen 9B and Tower+ 72B). The results indicate a modest advantage for Tower+, but with mutual acceptability in certain instances. These findings establish a viable semi-automatic framework for style guide integration in translation workflows, and motivate further investigation across broader domains, clients, and LPs.- Anthology ID:

- 2026.eamt-2.31
- Volume:
[Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2)](https://aclanthology.org/volumes/2026.eamt-2/)- Month:
[EAMT](https://aclanthology.org/venues/eamt/)- SIG:
- Publisher:
  • European Association for Machine Translation
- Note:
- Pages:
  • 114–119
- Language:
- URL:
[https://aclanthology.org/2026.eamt-2.31/](https://aclanthology.org/2026.eamt-2.31/)- DOI:
- Cite (ACL):
[Automated Information Extraction and Template Filling from Client Style Guides](https://aclanthology.org/2026.eamt-2.31/)(Graça et al., EAMT 2026)- PDF:
[https://aclanthology.org/2026.eamt-2.31.pdf](https://aclanthology.org/2026.eamt-2.31.pdf)
── more in #machine-learning 4 stories · sorted by recency
── more on @leonor graça 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/automated-informatio…] indexed:0 read:2min 2026-08-24 · —