🚀
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. Orchestration

Drafting linguistic resources

The following features are just ideas at this point, but if they seem useful we will integrate them into our roadmap.

We are hoping to add some core linguist-bot features to the Copilot roadmap. This will include the construction of glossary drafts, which is a crucial step in understanding the language structure. Simultaneously, we'll work on identifying key terms that are frequently used, as these will form the foundation of our translation database.

Alongside these, we're considering the development of grammar features, although we're still determining the specifics of this component. An additional feature we're contemplating is a 'getting started' walkthrough. This would involve users translating some key terms initially, and perhaps some of the most common words and phrases. The aim is to 'seed' the translation tool with content for predictions.

Examples of phrases that users could translate initially include "and he said" and "and they replied". We could also provide context-specific prompts, such as "Hey, we noticed you're starting the book of Mark. Here's some key people in Mark: [...]. How would you like to render these for now? Here's some common phrases: [...]". This approach could help us reconceptualize the task of Bible translation as 'translation of Biblical language' as an initial phase, rather than the more complex task of 'translation of biblical texts'.

Lastly, we're imagining the creation of a gamified points-building mini-game. In this game, the user would be asked to translate extremely simple or generic phrases. These translations would then be confirmed and strengthened when the app re-asks for known phrases, either in their original form or with additional variations. This could make the early drafting process more engaging and enjoyable for users.

PreviousMulti-Agent SimulationsNextIntelligent Functions Library

Last updated 1 year ago