🚀
Codex Editor
  • Project Overview
    • Welcome to Codex
    • Codex Editor
      • Features
      • What was Project Accelerate?
        • Project Philosophy
        • Steering Committee
    • Vision
      • Powerful Tools and Simplicity
      • Streamlining the Translation Process
      • Unopinionated Assistance
    • Architecture
    • Frequently Asked Questions
    • Translator Requirements
    • Roadmap
    • Why VS Code?
    • Multimodality
  • Translator's Copilot
    • What is Translator's Copilot?
    • Information Management
      • Resource Indexing
      • Greek/Hebrew Insights
      • Chat with Resources
      • Project-Based Insights
    • Translation Assistance
      • Translation Drafting
        • Prioritizing Semantics over Structures
        • Reranked Translation Suggestions
      • Quality Checking
        • Token matching evaluation
        • Few-shot evaluation
        • Fine-tuned Bible QA model
        • Character and word n-gram evaluation
        • Simulated GAN evaluation
        • Linguistic Anomaly Detection (LAD)
      • Back Translation
    • Orchestration
      • Translation Memory
      • Multi-Agent Simulations
      • Drafting linguistic resources
    • Intelligent Functions Library
  • Development
    • Codex Basics
      • Projects
      • The Editor
      • Extensions
        • Rendered Views
        • Language Servers
        • Custom Notebooks
        • Global State
    • Experimental Repositories
Powered by GitBook
On this page
  1. Translator's Copilot
  2. Translation Assistance
  3. Translation Drafting

Reranked Translation Suggestions

Semantic similarity between source verses as a tool for suggesting a disambiguated rendering from multiple possible options.

Would work best with semantic units, not just words, but we can initially implement with words only.

  • Source verse 1: “Jesus walked on the water”

  • Source verse 2: “Jesus said, give me some water to drink”

  • Source word ‘water’ - translated as ‘big blue wet thing’ in target rendering for source 1

  • Source word ‘water’ translated as ‘drinking stuff’ in source 2

Dictionary updated to note that there are two possible renderings of the ‘water’ entity in the source, and it notes the verse context for each rendering.

Later, when we want to suggest a rendering for ‘water’, we first check our new source verse, and see whether it is most similar to the verse that says ‘big blue wet thing’ in it, or else the verse that says ‘drinking stuff’ in it.

Suggest the most likely option accordingly.

Note: Semantic units - previous glosses apply to the largest entity in nested entities AND all children until there is a separate case where there’s only partial overlap between source and target

PreviousPrioritizing Semantics over StructuresNextQuality Checking

Last updated 1 year ago