Until now, Bing autocomplete provided instant answers by completing search queries, and PageZero as you type. Now, bing has improved autocomplete queries associated with academic papers and movies.
The improved autocomplete is the result of integration with TNR (Microsoft's Technology and Research team) and Bing semantic graph, that allow user to construct highly structured queries.
According to bing, academic suggestions launched earlier this year was built by Cognitive Services and Academic Search teams, is more intelligent now that explores graph relationships in real-time and generates the most relevant suggestions, even if Bing has never seen the query before. Scenarios include: "find all papers by an author," "find a paper written by particular co-authors," "find a paper about a specific topic presented at a conference," or "suggest titles or authors."
The feature explore the relationships between papers, authors, topics and publications through a large object graph.
In the second upgrade, bing allows users to find movies by formulating their queries by evaluating the user's natural language input, and then determining the user's intent with a lightning-fast runtime component to generate the most likely interpretations.
bing explains, "we don't just work with simple string representations. Instead we developed as set of rich objects capturing extremely detailed semantic interpretation of the query, its intent domain information, parts-of-speech mapping, and more."
Furtermore, bing notes, "this system can generate extensions to the query even if no user has ever typed them in before, allowing additional, never-seen-before suggestions to be generated.." "And it works on both academic papers and movies.
Here are some example movie queries that a user can formulate: "movies by director," "movies starring an actor in a particular genre, "movies from a particular year starring a certain actor," or "movies starring a pair of actors," bing said.