IRF Symposium 2007 - Programme

The IRF Symposium focused on five main problem areas within the patent information search and retrieval world as follows:

1. Data Quality

OCR errors in patent full-text documents
effective retrieval of misrecognised scanned documents
user errors in formulating queries and IR techniques to overcome them

2. Language Gap

machine translation of Chinese patents: an overview of the challenges
automatic machine translation – focus on Asian languages
cross lingual retrieval issues in the Korean language
what’s different with Chinese in cross-language IR?

3. Corpus Enrichment

focusing the search process to segments
a picture speaks in 1000 words: retrieving the information hidden in patents
presentation and searching of molecules in chemical patents
classification and industry-specific terms and keywords metadata
term semantics by association
automatic concept identification
developments in the evaluation of search engines.

4. Tools for Information Professionals

50 million patents further and we are still searching like 28 years ago
issues and approaches on interactive patent retrieval: evaluations of sessions rather than queries
how do we go about patent searching?
interfacing with search results
handling search results.

5. Tools for Management & Research

patent analysis from an IP perspective
patent mapping and visualization: what is the state of the art?

The 3rd IRF Symposium is placed under the motto “Benchmarking Relevance” and will especially focus on methodology and evaluation in patent searching and retrieval. Participants will have the opportunity to discover and test prototypical versions of the most innovative technologies in the market. read more

The 1st Information Retrieval Facility Conference provides a multi-disciplinary, scientific forum for researchers and aims at bringing young researchers into contact with industry at an early stage. The conference focuses on large scale research projects. read more