So how do you reach every person on the planet: Internationalization at Twitter
summary
Twitter claims language scale by combining tooling, open libraries and NLP rather than manual translation alone. translate.twitter.com exists for community localization, mobile contribution is underway, and Twitter officially supports 36 localized languages while content spans hundreds. Open projects include Twitter Korean Text and CLDR helpers in Ruby Java and JavaScript, plus an emoji set released 2014 that powers hashflags. Algorithms for language detection and relevance handle messy mixed‑language tweets and ranking on trends.
AI-written summary · about
chapters (8)
- 0:00Intro
- 1:08Access: Considerations
- 3:59Access: Twitter speaks my language
- 10:01Internationalization
- 14:27Localization
- 18:41Language Processing (NLP)
- 25:36Open Source, Open Standards
- 30:30Questions?
related talks
45mTranscend Language Barriers with Custom Machine Learning APIs: um...
37mMultilingual sentiment analysis & emotion detection based on social media data
43mBreaking the language barrier: how do we quickly add multilanguage support in our AI application?
51mAI for every language
45mSilkRoad: A Multilingual Communication Platform
16mBeyond Translation — Protecting and Scaling Global Processes with AI Speech Technology
19mDeep Into the Tweet
47mAya: Expanding the Worlds AI serves