Our proposal for the CLEF-IP 2012 Benchmarking Activity has been accepted. The Lab will be organized by the IFS, Vienna University of Technology in collaboration with the Chemical Biology Laboratory at NCI-Frederick, Fraunhofer SCAI and the University of Birmingham, School of Computer Science.

More details about CLEF-IP 2012 can be found on the project website at the Vienna University of Technology.

The CLEF-IP track was launched in 2009 to investigate IR techniques for patent retrieval and was part of the CLEF 2009 evaluation campaign.  In 2011, the track continues as a benchmarking activity of the CLEF 2011 conference.

There are four tasks in the 2011 track:

• Prior Art Candidate Search:  Find patent documents that are likely to constitute prior art to a given patent application.
• Classification:  Classify a given patent document according to the IPC system, up to the subclass level. A new optional sub-task is to classify a given patent document up to the group/subgroup level, when the subclass is given.
• New: Image-based Patent Retrieval: Find patent documents
  relevant to a given patent document containing images.
• New:  Image-based  Classification:  Categorize  given  patent  images  into pre-defined categories of images (such as graph, flowchart, drawing, etc.).

More details on each of the tasks are available on the dedicated web pages. Detailed information on the tasks such as description of the data, submission formats, etc. are available after registration.

The data collections are extracts of the MAREC dataset, containing over 2.6 million patent documents pertaining to 1.3 milion patents from the European Patent Office with content in English, German and French, and extended by documents from the WIPO.

The data for all tasks has been released. Prior to downloading it, participants must follow the instructions given under "How to Participate".

The CLEF-IP workshop took place on September 20th, in the frame of the CLEF confenrece in Amsterdam. The first part of the workshop was dedicated to presentations on how linguistic methods were applied to the Prior Art Candidates task and on Image Classification. The second part consisted of a session where various ways of continuing the CLEF-IP lab were discussed.