A patent document retrieval system addressing both semantic and syntactic properties

  • Authors:

  • Liang Chen;Naoyuki Tokuda;Hisahiro Adachi

  • Affiliations:

  • University of Northern British Columbia, BC, Canada;R & D Center, Sunflare Company, Tokyo, Japan;R & D Center, Sunflare Company, Tokyo, Japan

  • Venue:
  • PATENT '03 Proceedings of the ACL-2003 workshop on Patent corpus processing - Volume 20
  • Year:
  • 2003

Quantified Score

Hi-index 0.01

Visualization

Abstract

Combining the principle of Differential Latent Semantic Index (DLSI) (Chen et al., 2001) and the Template Matching Technique (Tokuda and Chen, 2001), we propose a new user queries-based patent document retrieval system by NLP technology. The DLSI method first narrows down the search space of a sought-after patent document by content search and the template matching technique then pins down the documents by exploiting the words-based template matching scheme by syntactic search. Compared with the synonymous search scheme by thesaurus dictionaries, the new method results in an improved overall retrieval efficiency of patent documents.