This blog post introduces the Semantic Telemetry project at Microsoft Research, which uses a data science approach to analyze how people interact with AI systems, specifically focusing on Copilot in Bing usage. It discusses the complexity of human-AI interactions and how they differ from traditional search.
- Topics: Copilot in Bing chats were analyzed for topic categorization. Technology (21%) was the most common topic, followed by Entertainment (12.8%), Health (11%), and others. Within technology, programming and scripting were prominent subtopics.
- Platform Differences: Mobile users tend to use Copilot for personal tasks, while desktop users engage in more professional activities.
Bing Web Search API enables safe, ad-free, location-aware search results, surfacing relevant information from billions of web documents. Help your users find what they're looking for from the world-wide-web by harnessing Bing's ability to comb billions of webpages, images, videos, and news with a single API call.
The article discusses the integration of Large Language Models (LLMs) and search engines, exploring two themes: Search4LLM, which focuses on enhancing LLMs using search engines, and LLM4Search, which looks at improving search engines with LLMs.
The aspirational goal of our Data Cleaning project at Microsoft Research 6 » (started in the year 2000) is to design and develop a domain independent horizontal platform for data cleaning, so that scalable vertical solutions such as address cleansing and product de-duplication can be developed over the platform with little programming effort. The basis for this goal is the observation that some fundamental concepts such as textual similarity and need to extract structured data from text are part of many data cleaning solutions
