Test collections with structured documents

IEEE Publications 1995 - 1997

From the IEEE Computer Society publications from 1995 to 1997 we distilled an XML document collection, with the purpose of serving as test collection for structured document retrieval.

• Prototype Application (down) with HyREX
• Delos Meta-Library Entry
• You can buy the raw data from IEEE. Don't hesitate to ask us for help when you want to convert the data to XML.

The Shakespeare Test Collection

The Shakespeare test collection consists of 37 Shakespeare plays marked up in XML by Jon Bosak, 43 queries and the appropriate relevance assessments and best entry points.

• Prototype Application (down) with HyREX