Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Projet
Knowledge Mining API
To better satisfy the requirements of different scenarios, we built a set of knowledge mining APIs using our technologies developed for Satori Pipeline, Bing QnA and our Enterprise Dictionary project. We are pleased to announce…
Projet
Digital Me
Digital Me: Toward Digitalizing Everybody in the World Introduction: Artificial Intelligence (AI) applications such as chat bots, software assistants etc. are attracting increasing attention from both academic and industry. Most existing work aim to assist…
Projet
Enterprise Dictionary
1. Project Introduction “Everyday we are faced with a sea of acronyms, ever changing group structures, and fast-tracked projects.” Currently, collation and curation of corporate knowledge is a painstaking manual process. We seek to move…
Projet
QnA Miner
Goal: Q&A is an important knowledge data to enable many scenarios like auto question answering in bot. This Q&A miner provide a platform to 1. Extract Q&A data automatically w/ human knowledge in loop. 2.…
Projet
Kable
Goal: Kable is to extract structured knowledge from semi-structured Web site. Around 25% Web pages are of semi-structured, which contains lots of knowledge and are template generated web pages. Kable can learn the template across…
Projet
Conceptualization
The Conceptualization model aims to map text format entities into semantic concept categories with some probabilities, which may depend on the context texts of the entities. As an example, “Microsoft” could be automatically mapped to…
Blog de recherche Microsoft
Boosting fitness and workplace performance looks to machine learning for answers
By Miran Lee, Principal Research Program Manager, Microsoft Research A field study exploring the usability of integrating fitness equipment into a workstation environment has researchers looking to tap next-generation machine learning innovations to address the…
Vidéo
Improving Reinforcement Learning with Human Input
Although reinforcement learning (RL) has had many successes, significant amounts of time and/or data can be required to reach acceptable performance. If agents or robots are to be deployed in real world environments, it is…
