Project Custom Decision
< Back to Cognitive Research Technologies main page Project Custom Decision is a cloud-based, contextual decision-making API that sharpens with experience. Project Custom Decision uses reinforcement learning in a new approach for personalizing content. Project…
Project Ink Analysis
< Back to Cognitive Research Technologies main page What is Project Ink Analysis Project Ink Analysis provides cloud APIs for understanding digital ink content. In addition to simply recognizing the words written by a user,…
Project Anomaly Finder
< Back to Cognitive Research Technologies main page Project Anomaly Finder was an experimental lab that helped monitor data over time and detect anomalies with machine learning that adapted to unique data by automatically applying…
Project Event Tracking
< Back to Cognitive Research Technologies main page Documentation Project Event Tracking is an API designed to help you find events associated with Wikipedia entities. Just start with an entity from Wikipedia, and the API…
Project Answer Search
< Back to Cognitive Research Technologies main page SubscribeDocumentation Project Answer Search API Project Answer Search enables you to enhance the user search experience of your sites and applications by instantly answering queries with relevant…
Project Conversation Learner
< Back to Cognitive Research Technologies main page Discover a new way to build and teach conversational interfaces Project Conversation Learner enables you to build and teach conversational interfaces that learn from example interactions. Unlike…
Project Knowledge Exploration
< Back to Cognitive Research Technologies main page DocumentationSDK Enable interactive search experiences over structured data via natural language inputs: Natural Language Understanding To interpret natural language queries as structured query expressions. Query Auto-Completion To…
Beyond spell checkers: Enhancing the editing process with deep learning
“Here’s my conference paper—what do you think?” After hours of agonizing over words and illustrations, sharing a draft document is a moment of great pride. All too often, this is shortly followed by embarrassment when…
Real World Reinforcement Learning
The mission of Real World Reinforcement Learning (Real-World RL) team is to develop learning methods, from foundations to real world applications, to empower people and organizations to make better decisions. The research enables the next…
Machine Reading Systems Are Becoming More Conversational
A team of researchers from the Natural Language Processing (NLP) Group at Microsoft Research Asia (MSRA) and the Speech Dialog Research Group at Microsoft Redmond are currently leading in the Conversational Question Answering (CoQA) Challenge…