Back to Details

lovstudio-translation-review

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

translation-review — Chinese-English Translation Review

translation-review — 中英翻译审核

Systematically compare a Chinese source document against its English translation, identify issues across 6 dimensions, and produce a prioritized review report.
系统地将中文源文档与其英文翻译版本进行对比，从6个维度识别问题，并生成带有优先级的审核报告。

When to Use

适用场景

  • User provides a Chinese original + English translation pair for review
  • User asks to check/proofread an English translation from Chinese
  • User mentions "翻译检查", "审校", "translation review"
  • 用户提供中文原文+英文翻译版本以供审核
  • 用户要求检查/校对从中文翻译而来的英文内容
  • 用户提及“翻译检查”“审校”“translation review”

Workflow (MANDATORY)

工作流程（必须遵守）

You MUST follow these steps in order:
你必须按以下顺序执行这些步骤：

Step 1: Collect Input

步骤1：收集输入信息

Use 
AskUserQuestion
to confirm before starting:
Ask the user:
  1. Document type — academic paper (SCI/EI), technical docs, business docs, general
  2. Domain — medicine, CS, law, finance, general (affects terminology checking)
  3. Focus areas — terminology accuracy, grammar, style, references, all (multi-select)
If the user has already provided context (e.g., "SCI 4区医学论文"), skip the obvious questions.
开始前使用
AskUserQuestion
确认以下信息：
询问用户：
  1. 文档类型 — 学术论文（SCI/EI）、技术文档、商务文档、通用文档
  2. 领域 — 医学、计算机科学（CS）、法律、金融、通用领域（影响术语检查）
  3. 重点关注领域 — 术语准确性、语法、风格、参考文献、全部（可多选）
如果用户已提供上下文（例如“SCI 4区医学论文”），则跳过明显无需询问的问题。

Step 2: Read Both Documents

步骤2：阅读两份文档

Read the Chinese source and English translation. For 
.docx
files:
bash
pandoc "<chinese_file>.docx" -t plain --wrap=none
pandoc "<english_file>.docx" -t plain --wrap=none
For 
.md
or 
.txt
files, read directly.
If files are large, read in sections (offset/limit) to stay within context.
阅读中文源文档和英文翻译版本。对于
.docx
文件：
bash
pandoc "<chinese_file>.docx" -t plain --wrap=none
pandoc "<english_file>.docx" -t plain --wrap=none
对于
.md
或
.txt
文件，直接阅读。
如果文件较大，分章节阅读（设置偏移量/限制）以控制上下文长度。

Step 3: Systematic Review

步骤3：系统性审核

Compare the two documents across 6 dimensions, in this order:
从以下6个维度对两份文档进行对比审核，顺序如下：

D1: Mistranslation (meaning changed)

D1：误译（语义改变）

  • Words/phrases translated to a different meaning
  • Omissions (content in Chinese missing from English)
  • Additions (content in English not in Chinese)
  • Pay special attention to domain-specific terms that have been incorrectly generalized or specialized
  • 词语/短语被译为不同含义
  • 遗漏（中文内容未出现在英文中）
  • 增添（英文中存在中文没有的内容）
  • 特别注意被错误泛化或专业化的领域特定术语

D2: Terminology Accuracy

D2：术语准确性

  • Domain-specific terms: check against standard English terminology
  • Abbreviation consistency: first occurrence should have full form + abbreviation
  • Proper nouns: names, institutions, gene/protein names, drug names
  • Units and measurements
  • 领域特定术语：对照标准英文术语检查
  • 缩写一致性：首次出现时需标注全称+缩写
  • 专有名词：姓名、机构、基因/蛋白质名称、药物名称
  • 单位与度量

D3: Grammar & Syntax

D3：语法与句法

  • Subject-verb agreement
  • Tense consistency (especially in Methods vs Results)
  • Article usage (a/an/the) — common error in Chinese-to-English
  • Dangling modifiers, run-on sentences
  • Passive voice overuse
  • 主谓一致
  • 时态一致性（尤其在方法与结果部分）
  • 冠词使用（a/an/the）——中译英常见错误
  • 悬垂修饰语、连写句
  • 被动语态过度使用

D4: Consistency

D4：一致性

  • Same Chinese term translated differently in different places
  • Formatting inconsistencies (capitalization, hyphenation, number style)
  • Heading style consistency
  • 同一中文术语在不同位置翻译不同
  • 格式不一致（大小写、连字符、数字格式）
  • 标题风格一致性

D5: References & Citations (academic papers only)

D5：参考文献与引用（仅针对学术论文）

  • Citation numbers match between Chinese and English versions
  • Reference format consistency (author names, journal abbreviations)
  • Missing author information in reference entries
  • In-text citation correctness
  • 引用编号在中英文版本中匹配
  • 参考文献格式一致性（作者姓名、期刊缩写）
  • 参考文献条目缺失作者信息
  • 文内引用正确性

D6: Style & Register

D6：风格与语体

  • Academic register appropriate for target journal
  • Overly verbose or literary phrasing
  • Chinese-influenced sentence structure (e.g., "through...method" patterns)
  • Paragraph length and structure
  • 学术语体符合目标期刊要求
  • 过于冗长或文学化的措辞
  • 受中文影响的句式结构（例如“通过……方法”模式）
  • 段落长度与结构

Step 4: Source Document Issues

步骤4：源文档问题

While reviewing, also note issues in the Chinese source that the English faithfully translates but are themselves incorrect. Flag these separately.
审核过程中，同时记录中文源文档中存在的、被英文忠实翻译但本身有误的问题。单独标记这些问题。

Step 5: Generate Report

步骤5：生成报告

Output a structured review report with the following format:
markdown
undefined
输出结构化审核报告，格式如下：
markdown
undefined

翻译审校报告 / Translation Review Report

翻译审校报告 / Translation Review Report

Document: [title] Reviewer: 手工川 (AI-assisted) Date: [YYYY-MM-DD] Domain: [domain] Document type: [type]
文档: [标题] 审核人: 手工川 (AI辅助) 日期: [YYYY-MM-DD] 领域: [领域] 文档类型: [类型]

Summary

摘要

[2-3 sentence overall assessment]
[2-3句话的整体评估]

A-Level Issues (Must Fix)

A级问题（必须修正）

A1. [Issue title]

A1. [问题标题]

Location: [section/paragraph] Original (CN): "..." Translation (EN): "..." Problem: [explanation] Suggested fix: → "..."
位置: [章节/段落] 原文（中）: "..." 译文（英）: "..." 问题说明: [解释] 修正建议: → "..."

B-Level Issues (Recommended)

B级问题（建议修正）

B1. [Issue title]

B1. [问题标题]

...
...

Source Document Issues

源文档问题

C1. [Issue title]

C1. [问题标题]

...
...

Priority Summary

优先级汇总

Priority#IssueImpact
Must fixA1......
...
优先级编号问题影响
必须修正A1......
...

Conclusion

结论

[Overall quality assessment + recommended next steps]
undefined
[整体质量评估 + 后续步骤建议]
undefined

Step 6: Save Report

步骤6：保存报告

Save the report to the same directory as the input files:
Filename: 
手工川-translation-review-{YYYY-MM-DD}-v0.1.md
If a file with this name exists, increment the version.
将报告保存至输入文件的同一目录：
文件名: 
手工川-translation-review-{YYYY-MM-DD}-v0.1.md
如果同名文件已存在，递增版本号。

Issue Severity Classification

问题严重程度分类

LevelCriteriaExamples
A (Must fix)Meaning changed, factual error, or would cause rejectionMistranslation, wrong terminology, reference number mismatch
B (Recommended)Awkward but understandable, or non-standard usageVerbose phrasing, minor grammar, style inconsistency
C (Source issue)Error in Chinese original, faithfully translatedWrong terminology in Chinese, factual inaccuracy
级别判定标准示例
A（必须修正）语义改变、事实错误或会导致被拒误译、术语错误、引用编号不匹配
B（建议修正）表达生硬但可理解，或非标准用法措辞冗长、轻微语法问题、风格不一致
C（源文档问题）中文原文有误，被忠实翻译中文术语错误、事实不准确

Domain-Specific Checklists

领域特定检查清单

Academic / SCI Papers

学术/SCI论文

  • Abstract: structured, matches body content
  • Keywords: standard MeSH or domain terms
  • Reference numbers: sequential, match between CN/EN versions
  • Figure/table captions: translated and consistent
  • Statistical reporting: p-values, CI format
  • 摘要：结构化，与正文内容匹配
  • 关键词：标准MeSH或领域术语
  • 引用编号：连续，中英文版本匹配
  • 图/表标题：已翻译且一致
  • 统计报告：p值、置信区间（CI）格式

Medical / Biomedical

医学/生物医学

  • Disease names: ICD/MeSH standard
  • Gene/protein names: HUGO/UniProt standard (italics for genes)
  • Drug names: INN (International Nonproprietary Names)
  • Anatomical terms: Terminologia Anatomica standard
  • 疾病名称：符合ICD/MeSH标准
  • 基因/蛋白质名称：符合HUGO/UniProt标准（基因用斜体）
  • 药物名称：符合INN（国际非专利名称）标准
  • 解剖学术语：符合Terminologia Anatomica标准

Technical Documentation

技术文档

  • UI strings: consistent with product localization
  • Code snippets: untranslated, syntax preserved
  • API terms: match official documentation
  • UI字符串：与产品本地化一致
  • 代码片段：不翻译，保留语法
  • API术语：与官方文档匹配