Automatic detection of treatment relationships for patent retrieval

We devise a method for automatically detecting treatment relationships using lexico-syntactic patterns and its application to medical-oriented patent retrieval. This process for detecting treatment relationships involves finding lexico-syntactic patterns that are highly indicative of treatment relationships and also producing classification rules for those patterns. This treatment relationship detection process is then used in a system to find treatment relationships based on a user query in a medical patent source. The query will consist of terms that the user wants to find in the subject or object of a treatment relationship. This is of great interest to both patent examiners and patent applicants as they search for prior art. Through the use of classification rules, this system was able to achieve a precision of 85.81% on a set of 20 test queries. Categories and Subject Descriptors H.3.1 [Information Storage and Retrieval]: Content Analysis and Indexing

• Type: Conference
• Year: 2008
• Where: CIKM
• Authors: Aaron Chu, Shigeyuki Sakurai, Alfonso F. Cardenas
• Keywords: CIKM 2008, Information Management, Lexico-syntactic Patterns, Medical-oriented Patent Retrieval, Treatment Relationship