|More from: | ZDNET |||
When IBM’s Watson computer beat two world champions at the game show Jeopardy! in 2011, it was a moment to marvel at how a machine could take comprehend the language of a question and could mine its vast memory for an appropriate response.
Google scientists have found another use for Jeopardy! questions, having little to do with understanding human speech and more about how computers communicate with one another.
And this week, they’ve made that work an open-source software tool available on GitHub to anyone using Google’s TensorFlow framework for machine learning.
“Active Question Answering,” or Active QA, as the TensorFlow package is called, will reformulate a given English-language question into multiple different re-wordings, and find
About | ZDNET |
ZDNet brings together the reach of global and the depth of local, delivering 24/7 news coverage and analysis on the trends, technologies and opportunities that matter to IT professionals and decision makers.
Whatever your role in the IT buying cycle, ZDNet provides support -- from investigating options to optimizing a solution. Whether you want to follow hot topics or emerging trends, or keep up to date with the latest news and events, ZDNet is the destination for professionals seeking to research technology-related issues, and solve business technology problems.