Experimentation and Continuous Improvement at Bing

One technical problem in Web search is how best to measure the quality of search results. Our powerful machine learning systems correct the spelling of your query, interpret your search intent, differentiate quality pages from junk, rank documents from our index of tens of billions of documents, and optimize whole-page layout. These systems, and many more, must all be optimized towards user satisfaction. The problem is that there is no perfect...
Read More

Ten Blue Links No More: Dynamic Page Sizing

Most search engines still provide a fixed number of web links on the search results page, typically 10 blue links in addition to instant answers. But are 10 blue links the right number of links for all queries and scenarios? Intuitively it doesn’t seem so. For example, showing fewer search results in navigational queries may enable users get to their desired URL faster. Also, users may benefit from seeing more blue links when they return to...
Read More

A Deeper Look at Autosuggest

Autosuggest enables people to select a query from a pull-down menu of suggestions when they start typing a query. You often find the query you want in the menu and select it, saving you extra keystrokes while reducing a chance of misspelling. It is a feature that people may take for granted but upon examination it involves a tremendous amount of technical sophistication and computational horsepower. In this blog Antonio Gulli who is our...
Read More

Building a State-of-the-Art Speller

Is it Swarzinegar, Swarneger, Scwarznagger or Schwartiznegar? These are just a few of more than 2,000 different ways users on Bing have typed their queries in hope of searching for “Schwarzenegger.” The aim of the Bing Speller is to correct these queries so users receive relevant web results that match their intent even when their query is misspelt. A great speller makes a search engine feel like magic to the users. In this blog my...
Read More

Behind the Bing It On Challenge

As I mentioned in my original post there has never been a more exciting or challenging time to be in the search space. The core to a great search engine has been and will always remain the same: delivering relevant, comprehensive and unbiased results that people can trust. We use thousands of signals from queries to documents and user feedback to determine the best search results and in turn make hundreds of improvements to our features every year...
Read More

Minimizing Answer Defects

Back in March, Jan Pedersen explored the topic of Whole Page Relevance. In the post, he outlined how Bing ranks media objects to deliver a rich set of results that go beyond just web pages using machine learning techniques. These objects include videos, images, maps, news items and assorted media objects or what we call answers. Today, Kieran McDonald will detail how we ensure that the answers are not defective and the results match the intent of...
Read More

Friends and Experts

  The foundation of web search has been built on keywords, links and clicks pointing to pages. This approach is great for finding web sites but search is more than about simply finding pages. With the help of social networks, people are able to share nearly everything they do in digital form and offer their opinions on almost every conceivable topic. From real-time streams to social conversations, connections are created that present the...
Read More

Scientific Research Contributions (I)

Researchers and engineers in Microsoft Research (MSR) and Bing R&D have been working closely together and have made significant contributions to the science of search. These contributions often start as basic research ideas published as scientific articles in international conferences and journals. These articles are reviewed by search experts from industry and academic institutions around the world, and only those that significantly advance...
Read More

To Err is Human

At Bing we’re committed to delivering you the best possible results.  While teams of researchers, machine learning experts and data miners continually improve our core spelling and ranking components, the reality is that some defects have historically slipped through the cracks. This is partly because search relies on people to teach the system and, since people make mistakes, some defects are introduced.  Our recent release, takes...
Read More

Reducing Junk

Everyone has experienced trying to follow a link that didn’t work. The link may have led to a page that is no longer available, or to a parked domain page. It can also be frustrating to find a search result page that has a missing or garbled description of where the link may take you. Considering the enormity of the web and the complexity of linking web documents , a key challenge for web search quality is the search engine’s...
Read More