Synonym Mining

Established: January 7, 2014

The same entity is often referred to in a variety of ways. For example, the camera Canon 600d is also referred to as “canon rebel t3i”, the celebrity Jennifer Lopez is also referred to as “jlo” and Seattle Tacoma International Airport is also referred to as “sea tac”. These are known as synonyms. Without knowledge of synonyms, many applications like e-commerce search will fail to return relevant results. We leverage the data assets amassed by Bing to automatically mine such synonyms.

One of the main insights is to use Bing’s query log to mine synonyms. However, simple techniques like using co-click frequencies are not adequate; we developed new features like pseudo-document similarity and context similarity. Furthermore, we leverage other data sources like web lists, web tables and certain text patterns to mine synonyms.

Impact

Our synonym research had tremendous impact of several Microsoft products and services over the years:

  • Synonyms technology is used by Bing’s entity-linking technology which in turn powers several applications like Bing Snapp (opens in new tab), Ask Cortana (opens in new tab), and Bing Knowledge Widget (opens in new tab). (2015)
  • We worked closely with Bing and Azure DataMarket teams to release the the Synonym API (opens in new tab) so that external developers can integrate the synonym knowledge into their applications (e.g., e-commerce search application). It is part of Bing Dev Center (opens in new tab) along with the other Bing APIs. (2012)
  • We have integrated our synonym technology into Dynamics AX for Retail to power their e-commerce search functionality. (2013)
  • Synonyms technology is used by Bing Sports as well to return relevant information when people search for sports teams, players, leagues, etc. For example, when users search for `tampabaybucs (opens in new tab)’, they leverage our synonyms to return “information card” about Tampa Bay Buccaneers. (2012)
  • Synonym technology is used to enhance product search in Bing Shopping (2010)
  • Synonym technology is used by Bing Ads for matching keyword queries with advertisements (2010)
Other contributors: Dong Xin, Venkatesh Ganti, Tao Cheng
Past interns: Manish Gupta, Bilyana Taneva, Tomasz Tylenda

People

Portrait of Kaushik Chakrabarti

Kaushik Chakrabarti

Senior Researcher

Portrait of Surajit Chaudhuri

Surajit Chaudhuri

Technical Fellow, Data Platforms and Analytics

Portrait of Yeye He

Yeye He

Senior Principal Researcher