Detecting duplicates in a shared knowledge base

A method for supporting curation of a new item in a searchable knowledge base, wherein the searchable knowledge base includes a plurality of items, said method comprising:

• mining one or more search queries of the searchable knowledge base, wherein each of the one or more search queries includes a plurality of the plurality of items;
• running at least one of the one or more search queries against the searchable knowledge base;
• determining one or more items using a processor, wherein each of the one or more items include a correlation value exceeding a threshold, wherein the correlation value for the each of the one or more items is based upon a frequency the each of the one or more items co-occur with the new item in at least one of the at least one of the one or more search queries;
• providing at least one of the one or more items to a curator, wherein the curator reviews the at least one of the one or more items.

A system for supporting curation of items in a searchable knowledge base, said system comprising:

• a mining module adapted to mine one or more search queries of the searchable knowledge base, wherein each of the one or more search queries includes a plurality of the items;
• a correlation module adapted to determine one or more pairs of items using a processor, wherein each of the one or more pairs of items include a correlation value exceeding a threshold, wherein the correlation value for the each of the one or more pairs of items is based upon a frequency the items of the each of the one or more pairs of items co-occur within the one or more search queries;
• and,
• an interface adapted to provide at least one of the one or more pairs of items to a curator, wherein the curator reviews the one or more pairs of items.

A system for supporting curation of a new item in a searchable knowledge base, wherein the searchable knowledge base includes a plurality of items, said system comprising:

• a mining module adapted to mine one or more search queries of the searchable knowledge base, wherein each of the one or more search queries includes a plurality of the plurality of items;
• a search module adapted to run at least one of the one or more search queries against the searchable knowledge base;
• a correlation module adapted to determine one or more items using a processor, wherein each of the one or more items include a correlation value exceeding a threshold, wherein the correlation value for the each of the one or more items is based upon a frequency the each of the one or more items co-occur with the new item in at least one of the at least one of the one or more search queries;
• an interface module adapted to provide at least one of the one or more items to a curator, wherein the curator reviews the at least one of the one or more items.