| parent | nav_order | title | description |
|---|---|---|---|
Contributing |
5 |
Roadmap |
Content roadmap for Machine Translate |
{% include collapsible_toc.html %}
- History [#65]
- FAQ
Rule-based machine translationStatistical machine translationNeural machine translation- Transformers [#73]
- Byte-pair encoding [#75]
- Customisation / Consulting providers [#29]
- Lexicon [#64]
- Corpus [#109]
String- Token [#111]
- n-gram [#108]
- Vector [#112]
Language model- Sentence splitting [#174]
- Word embeddings [#173]
Parallel data- File formats [#80]
- Data augmentation [#162]
- Back-translation (and back-copying) [#81]
Filtering- Training [#83]
Adaptive- Context [#113]
- Glossaries [#84]
- Controlled language [#85]
- Tuning [#163]
- Crawling [#72]
- Tokenisation [#73]
- Human-in-the-loop [#76]
- Unsupervised machine translation [#132]
- Zero-shot machine translation [#133]
Translation and localisationMultilingual searchTranslation for SEOCommerce and marketplacesSocial networksLive chatUser-generated content- Website translation [#160]
Gaming- Multilingual models [#66]
- Bridging (pivot languages [#67]
- Related-language translation [#68]
Multi-engine machine translationTags and placeholders- Formality and gender [#69]
- Morphology (incl. agglutination) [#70]
- Alignment (and term extraction) [#71]
- Pricing [#77]
Data confidentiality- Licensing and terms [#78]
Companies / Startups / AcquisitionsProducts / Providers- Talent / Education / Jobs [#79]
- CAT integration
- Speech translation [#90]
- Sign language translation [#91]
- Image translation [#92]
- Input correction [#93]
- Transliteration [#94]
- Language identification [#95]
- Long-tail languages / How to get machine translation for your language [#96]
- Language variants (fr-CA, en-UK…) [#97]
- Arabic [#98]
- Japanese [#99]
- Indic languages [#100]
- Russian [#164]
- Czech [#165]
- German [#166]
- Chinese [#101]
- Spanish [#102]
- Low-resource languages [#167]