Query Terms Extraction from Patent Document for Invalidity Search.

Abstract

This paper describes our patent retrieval system participated in the NTCIR-5 Patent Retrieval Task, Document Retrieval Subtask. The main scope of our method is the appropriate query expansion to improve recall. We extracted query terms from the topic claim, and expanded query terms extracted from sentences explained in the patent document including the topic claim. The explanation sentences were extracted by the method based on pattern matching and by the method based on the longest common subsequence length.