Microsoft posted on its research blog that is has launched Speller100, spelling correction models, to help Microsoft Bing Search do better at spelling corrections. Microsoft said 15% "about 15% of queries submitted by customers have misspellings" so this is needed.
Microsoft said it has "recently launched our large-scale multilingual spelling correction models worldwide with high precision and high recall in 100-plus languages! These models, technology we collectively call Speller100." Speller100 is currently used "to improve search results for these languages in Bing," Microsoft said.
Microsoft shared some examples including Query: {значење обединети нацииѐ} in Macedonian, translation {meaning united nations} Should be spelled as {значење обединети нации}.
And Query: {лацінскі алльфабэт} in Belarusian (be), translation {latin alphabet} Should be spelled as {лацінскі альфабэт}:
There are more examples in the Microsoft blog post.
Frédéric Dubut wrote on Twitter "With the web skewing towards a handful of popular languages, it is so important to go the extra mile and make sure our products work well in *all* languages. Very proud of the Speller team and equally excited to improve Bing search results in 100+ languages!"
How has this helped Bing do better? Well, they wrote " Speller100 is the most comprehensive spelling correction system ever made in terms of language coverage and accuracy. With this technology, we have improved the search results for all Bing users by expanding accurate spelling correction to over 100 languages. We have observed a double-digit improvement in both spelling correction precision and recall. After conducting Bing online A/B testing, here are the results:"
- The number of pages with no results reduced by up to 30%.
- The number of times users had to manually reformulate their query reduced by 5%. The number of times users clicked on our spelling suggestion increased from single digits to 67%.
- The number of times users clicked on any item on the page went from single digits to 70%.
Forum discussion at Twitter.
