In its Search Quality Insights, series, today, Dr. William Ramsey, Principal Development Manager, Core Search, Bing R&D posted that they have made many improvements to Related Searches beyond relevance in terms of formatting, reducing duplicated terms, and avoiding showing adult content under moderate or safe search settings.
"The beauty of search is that it relies on people to teach the system and as such, there will always be defects. Our hope is to reduce the rate and severity of defects so you can do less searching and get more done," Ramsey said ending the post.
Ramsey said, one of the major sources of defects pertains to what we call "URL queries."
"These are queries like "facebook.com" or "yahoo.com/mail" where the query looks like a URL. At first glance, you might think this is a simple problem for a search engine. After all, we've billions of URLs - how hard can it be to find a match on one?"
In reality, this type of query is actually quite complicated. Because we're all human, people use countless spelling variants.
He goes on to explain, "For instance, "facebook.com" has over a thousand different variants such as "facebookc.om", "facbook.com", and "ww.faceboo.omc". On top of the spelling errors, people don't always know the correct URL. We also commonly see permutations of URLs such as "yahoo.com/mail" when the correct URL is "mail.yahoo.com". Even if we figure out your intent, the multitude of spammers and squatters out there present another challenge. Spammers prey on variants of top domains or URLs that aren't quite spam like for e.g. facebooklogin.net (most people just want to login to facebook.com)."
Ramsey, said, our defect reduction efforts in this class of queries focused on three main areas:
- "The first was correctly identifying the URLs that we can correct. By identifying the troublesome URLs, we avoid problems such as including spam results like searscardcom.com.
- The second effort involved expanding our ability to model the types of errors that users make based on how people are using Bing. By recognizing patterns in billions of logs, we are able to fix common spelling errors in URLs.
- Lastly we analyzed billions of sessions to find patterns so that users looking for sites like "swair.com" would eventually end up on the intended site "southwest.com"."
Another example applies to machine learning models that would consider a query like "facebook login.com" to be equivalent to "facebooklogin.net." It's very common for people to type a ".com" when they want a ".net" or ".org" domain. In addition, it's also common for people to type queries like "bed bath and beyond.com" when they are looking for bedbathandbeyond.com.
"Our models have adapted to these patterns and now concatenate the terms and change ".com" to ".net" resulting in a seemingly unlikely but ultimately reliable interpretation of the query. By looking at several sources of user behavior we were able to refine our models to correctly deliver users what they intended," he said.
Removing Superfluous Recourse Links:
One of the critical components of a search engine is the query alterations component that performs spelling and query expansion. "Recourse Links are the phrases that occur underneath the query box that indicate that we changed your query due to spelling or expansion and give you the ability to turn off all of our alterations as a recourse," he explains.
"In the past we used to show synonyms as part of our recourse links and this would open up some surface area for showing embarrassing alterations that either were off-topic or were superfluous. The query "define interesting" highlights an example where the recourse link was unnecessary. Even though expanding "define" to "definition" helped the ranker surface a better match it didn't lead to a better user experience. In this case, showing the Recourse Link didn't enhance the experience."
"While we've removed the Recourse Links in cases where we are very confident that they add little value or distract users, we will continue to show them when there's a chance our query modifications are not what the user actually wanted," he said.
"When Bing alters some of the words in the query to synonyms, the recourse link may not add as much value, so we've changed the text color to black in order to make it more subtle and have provided a better explanation for the user."
Improved Related Searches are a set of queries that might be related to your initial query. "We used to show Related Searches on the left side of the search results but are now showing them on the right side of the search results and occasionally in-line with the web results," he said.
Sometimes our query expansion systems will cause the Related Searches to be off-topic. By improving our relevance models we were able to fix several of these sorts of defects.