ABSTRACT
Advances in artificial intelligence have improved machine understanding of speech, images, and natural language. This in turn has allowed us to greatly enhance the intelligence of products such as Bing and Cortana. This keynote describes our continuing journey beyond keyword-driven systems, into dialog and intelligent agent functionality, helping our users "research more, search less".
Modern systems attempt to provide concise direct answers, which can fit on a small screen or become a spoken response. To find such answers, Microsoft can draw from a uniquely broad inventory of data sources such as the Bing Web & Knowledge graphs, the workplace graph of Office 365, and the Microsoft Academic Graph. Since these graphs contain a lot of text information, we apply machine reading and comprehension technology to extract concise answers. Microsoft has entries frequently topping the leaderboards in the community»s machine reading contests.
To select the right answers, we use deep multi-task learning to develop a vector representation that is usable across multiple data sources and scenarios. This is combined with a large-scale data processing and serving infrastructure. We use this not only to find a single answer, but also to find multiple answers in cases where multiple valid perspectives exist. In the case of numeric answers, we provide some context to help users understand what the numbers mean. This is part of our effort to consider not just IQ but EQ in our conversational systems, where the chatbot Xiaoice leads the way in establishing a human connection, to develop long and sustained conversations. These advances improve product quality, enable new user experiences and have challenged us to rethink the entire intelligent search platform at Microsoft.
Recommendations
Identifying popular search goals behind search queries to improve web search ranking
AIRS'11: Proceedings of the 7th Asia conference on Information Retrieval TechnologyWeb users usually have a certain search goal before they submit a search query. However, many laypersons can't transform their search goals into suitable queries. Thus, understanding original search goals behind a query is very important for search ...
Re-ranking search results using query logs
CIKM '06: Proceedings of the 15th ACM international conference on Information and knowledge managementThis work addresses two common problems in search, frequently occurring with underspecified user queries: the top-ranked results for such queries may not contain documents relevant to the user's search intent, and fresh and relevant pages may not get ...
Comments