---
id: two-stage-user-styled-translation
title: Two-stage styled translation exists only in pieces
version: 1
published: '2026-10-27'
updated: '2026-10-27'
author: Hiina
produced-by: Claude deep-research run with citation checking
model: claude-opus-5-5
sources-through: '2026-10-25'
status: current
takeaway: No system yet joins an offline per-line meaning record to a cheap user-styled
  renderer; build it with closed-class style flags in code, the Japanese kept in the
  prompt, and style-keyed render caches.
topics:
- machine-translation
- localization
- japanese-learning
- llm-evaluation
sections: 12
---

Index of everything on this site: https://ai.hiina.space/index.md

# Two-stage styled translation exists only in pieces

- Author: Hiina (hiina@hiina.space)
- Produced by: Claude deep-research run with citation checking
- Version: 1 · published 2026-10-27 · updated 2026-10-27 · status: current
- Canonical: https://ai.hiina.space/reports/two-stage-user-styled-translation.md (this version as one file: https://ai.hiina.space/reports/two-stage-user-styled-translation/v1.md)
- Takeaway: No system yet joins an offline per-line meaning record to a cheap user-styled renderer; build it with closed-class style flags in code, the Japanese kept in the prompt, and style-keyed render caches.
- Topics: machine-translation, localization, [japanese-learning](https://ai.hiina.space/topics/japanese-learning.md), [llm-evaluation](https://ai.hiina.space/topics/llm-evaluation.md)
- Model: claude-opus-5-5
- Sources through: 2026-10-25
- Whole report as one file (75 KB; fetch tools may truncate it, so prefer the section pages below or download with curl): https://ai.hiina.space/reports/two-stage-user-styled-translation/full.md

The question behind this report: could Japanese game or visual novel (VN) text be translated in two stages? First, an expensive offline pass turns each line into a stored, language-neutral record of meaning, context and voice. Then a separate cheap renderer turns that record plus a reader's style profile (keep honorifics or not, literal or localised puns, even "talk like a pirate") into the line actually displayed. The report surveys shipped localisation practice, string formats, machine-translation research, live VN translation tools and dialogue-system design. It then proposes a record schema, a caching design and a ladder of experiments, and ties the same record to a Japanese-learning reading overlay.

## Contents

- [1. Summary](https://ai.hiina.space/reports/two-stage-user-styled-translation/01-summary.md) (included below)
- [2. Humans ship variants only where the choice is closed-class](https://ai.hiina.space/reports/two-stage-user-styled-translation/02-humans-ship-variants-only-where-the-choice.md) (11 KB)
- [3. Research covers each stage separately, and the joint is untested](https://ai.hiina.space/reports/two-stage-user-styled-translation/03-research-covers-each-stage-separately-and-the.md) (10 KB)
- [4. Live tools are single-stage translators with a prompt box](https://ai.hiina.space/reports/two-stage-user-styled-translation/04-live-tools-are-single-stage-translators-with.md) (9 KB)
- [5. A small renderer is plausible; measuring it honestly is the hard part](https://ai.hiina.space/reports/two-stage-user-styled-translation/05-a-small-renderer-is-plausible-measuring-it.md) (6 KB)
- [6. Game dialogue systems supply the field vocabulary](https://ai.hiina.space/reports/two-stage-user-styled-translation/06-game-dialogue-systems-supply-the-field-vocabulary.md) (3 KB)
- [7. A concrete record design, and where the cache sits](https://ai.hiina.space/reports/two-stage-user-styled-translation/07-a-concrete-record-design-and-where-the.md) (8 KB)
- [8. The same record drives the learner overlay](https://ai.hiina.space/reports/two-stage-user-styled-translation/08-the-same-record-drives-the-learner-overlay.md) (2 KB)
- [9. Real gaps, as far as this search reached](https://ai.hiina.space/reports/two-stage-user-styled-translation/09-real-gaps-as-far-as-this-search.md) (1 KB)
- [10. Candidate experiments, cheapest first](https://ai.hiina.space/reports/two-stage-user-styled-translation/10-candidate-experiments-cheapest-first.md) (3 KB)
- [11. Conclusion](https://ai.hiina.space/reports/two-stage-user-styled-translation/11-conclusion.md) (1 KB)
- [12. Sources](https://ai.hiina.space/reports/two-stage-user-styled-translation/12-sources.md) (11 KB)

## 1. Summary

Every layer of the pipeline has precedent, but this search found no system that assembles them: an offline pass that turns Japanese game or VN text into a stored, language-neutral record of meaning, context and voice, plus a separate cheap renderer that turns that record and a user style profile into the displayed line. The nearest real systems each own one layer. **Fan teams already ship static variants**: the Committee of Zero Steam patch for Steins;Gate 0 added an "Option to include Japanese honorifics in text" ([Committee of Zero project page](http://sonome.dareno.me/projects/sg0-steam.html)), and Square Enix shipped two selectable scripts for Final Fantasy Tactics: The Ivalice Chronicles ([Inverse](https://www.inverse.com/gaming/ivalice-chronicles-final-fantasy-tactics-japanese-only-feature-english-version), secondary). **Localisation formats already branch at display time**: MessageFormat 2 and Fluent select variants on any string variable, so a `$honorifics` selector is legal today, though every example in their documentation branches on grammar, not style ([UTS #35 Part 9](https://unicode.org/reports/tr35/tr35-messageFormat.html); [Fluent selectors](https://projectfluent.org/fluent/guide/selectors.html)). **Offline context extraction already exists in VN tooling**: GalTransl builds a character dictionary with an LLM pass over the script, keeps a per-line JSON cache, and can rebuild output from that cache without calling a model ([GalTransl README_EN](https://github.com/GalTransl/GalTransl/blob/main/README_EN.md); [GalTranslPP](https://github.com/julixian/GalTranslPP)). **The split between planning and wording is old NLG practice**: a symbolic planner feeding a neural realiser cut omissions from 41 to 6 on WebNLG at equal BLEU ([Moryossef et al. 2019](https://arxiv.org/pdf/1904.03396)).

What is missing is the joint. Live tools (LunaTranslator, XUnity plugins, VNTranslator, UGTLive) are single-stage translators with a free-text prompt box. Their caches are keyed by source string and store final text. In this search, none documented a structured style setting such as an honorifics toggle, and none stored more than one rendering per line ([Luna docs](https://docs.lunatranslator.org/en/guochandamoxing.html); [XUnity README](https://github.com/bbepis/XUnity.AutoTranslator/blob/master/README.md)). In research, formality control works well in the English-to-Japanese direction, but this search found no study of rendering Japanese honorifics and register into English under a user setting, and none that feeds an LLM-written scene description to a separate weaker renderer.

The evidence supports a specific shape for the design. Put hard, closed-class facts (names, address terms, honorific spans, register) in structured fields, and apply the closed-class toggles in code wherever possible. A rule-based Japanese verb editor kept formality accuracy at 95.5% formal and 100% informal, where a learned seq2seq post-editor collapsed informal accuracy to 26.2% ([Amazon IWSLT 2022](https://aclanthology.org/2022.iwslt-1.32.pdf)). Keep the Japanese source in the renderer's prompt, because every pivot representation tested so far loses meaning. Cache renders by line ID, record version and style hash, and pre-render ahead of the reader. Evaluate with targeted programmatic checks and a cross-family judge, because BLEU and COMET-class metrics either saturate or punish exactly the changes a style setting asks for.

The same record is the natural backbone for a Japanese-learning reading overlay, described in a companion report on Japanese learning and Anki tooling. A record that already holds lemma IDs, a literal gloss, register notes and a neutral translation turns rungs 4 and 5 of that overlay's hint ladder into a lookup plus a short render, and makes its clause-level hybrid mode tractable. The cheapest useful first step is an afternoon-sized benchmark on about 300 lines of a VN script the experimenter owns: frontier-made records rendered by a local 8B or 14B model under five style profiles, measured against direct frontier translation for fidelity, style compliance and per-line latency on a single 24 GB consumer GPU. That run also answers the overlay design's open latency question.

Next section: https://ai.hiina.space/reports/two-stage-user-styled-translation/02-humans-ship-variants-only-where-the-choice.md

---

Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space