TLDR - I used multilingual unsupervised methods (MUSE) to train cross-lingual word embeddings for over 500 languages. I then used these embeddings to extract components of the phrase “wash your hands” from existing target language documents. This resulted in translations of “wash your hands” in 510 languages not currently supported in any public translation platform.
You might not know, but there are currently 7,117 languages spoken in the world . That’s right, languages. Not dialects, but living languages! However, much of the world’s digital media is available in only a couple dozen languages, and translation platforms like Google Translate support around 100 languages. This reality means that there are billions of people around the world that are marginalized due to a lack of timely access to information. The current coronavirus (COVID-19) pandemic has made this painfully clear, and it has stressed the need for immediate, rapid translation of health-related phrases (like “wash your hands” and “social distancing”) into the long tail of languages.
以上就是本文的全部内容，希望本文的内容对大家的学习或者工作能带来一定的帮助，也希望大家多多支持 码农网
猜你喜欢:
本站部分资源来源于网络，本站转载出于传递更多信息之目的，版权归原作者或者来源机构所有，如转载稿涉及版权问题，请联系我们。
C++标准库（第2版）
Nicolai M. Josuttis / 侯捷 / 电子工业出版社 / 2015-6 / 186.00元
《C++标准库（第2版）》是全球C++经典权威参考书籍时隔12年，基于C++11标准的全新重大升级。标准库提供了一组公共类和接口，极大地拓展了C++语言核心功能。《C++标准库（第2版）》详细讲解了每一标准库组件，包括其设计目的和方法、复杂概念的剖析、实用而高效的编程细节、存在的陷阱、重要的类和函数，又辅以大量用C++11标准实现的实用代码范例。除覆盖全新组件、特性外，《C++标准库（第2版）》一......一起来看看 《C++标准库（第2版）》 这本书的介绍吧!
