TREC-CHEM '09

Based on the important progresses made in information retrieval (IR) in terms of theoretical models and evaluations, more and more attention has recently been paid to the research in domain specific IR, as evidenced by the organization of Genomics and Legal tracks in TREC. Now is the right time to carry out large scale evaluations on chemistry datasets in order to promote the research in chemical IR in general and chemical patent IR in particular.

The IRF, in collaboration with University College London and York University Canada, and with the support of the National Institute for Science and Technology (NIST), organizes a chemical IR track in TREC in order to address the challenges in chemical and patent IR. We will provide a test collection composed of over 1.2million full-text chemical patents and 50 thousands research papers from the Royal Society of Chemistry, UK. The aim is to identify how current IR methods adapt to text containing chemical names and formulas. Without making it a prerequisite, we encourage participants to use entity identification methods to extract and index chemicals. The evaluation process will be a combination of the pooling/sampling/expert evaluation approached frequently used in TREC and an automatic evaluation method based on references in patent documents.

 

Co-ordinators:

  • John Tait, Information Retrieval Facility
  • Jianhan Zhu, University College London
  • Xiangji Huang, York University Canada
  • Mihai Lupu, Information Retrieval Facility

For further information please sign up :
http://mail.ir-facility.org/mailman/listinfo/trec-chem or check our wiki page.

 

Contact

Mihai Lupu: m.lupu@ir-facility.org

 

TREC-CHEM WIKI

You can find all information about the TREC Chemistry Track at the .