Hisao Mase

Proposal of two-stage patent retrieval method considering the claim structure

The importance of patents is increasing in global society. In preparing a patent application, it is essential to search for related patents that may invalidate the invention. However, it is time-consuming to identify them among the millions of patents. This article proposes a patent-retrieval method that considers a claim structure for a more accurate search for invalidity. This method uses a claim text as input; it consists of two retrieval stages. In stage 1, general text analysis and retrieval methods are applied to improve recall. In stage 2, the top N documents retrieved in stage 1 are rearranged to improve precision by applying text analysis and retrieval methods using the claim structure. Our two-stage retrieval introduces five precision-oriented analysis and retrieval methods: query-term extraction from a portion of a claim text that describes the characteristics of a claim; query term-weighting without term frequency; query term-weighting with “measurement terms”; text retrieval using only claims as a target; and calculating the relevant score by “partially” adding scores in stage 2 to those in stage 1. Evaluation results using test sets of the NTCIR4 Patent Retrieval Task show that our methods are effective, though the degree of the effectiveness varies depending on the test sets.

Perspectives on reuse process support systems for document-type knowledge

Reusing documents as intellectual assets is one way of improving productivity and quality of products and services. The reuse process is well-known to make effective use of document-type intellectual assets and consists of four parts: (1) collecting and accumulating documents, (2) searching and browsing documents, (3) extracting and identifying documents, and (4) creating new documents. We describe problems in reusing document-type knowledge and propose solutions for each problem. The most important point in reusing documents effectively is to accumulate them in an appropriate format and accurately identify them by content.

Building Natural Language Interface - Its Methodology and Tools

Abstract This paper presents methodology and tools for building natural language interface between users and application systems. The goal of this research is to allow any system designer to implement a natural language interface. A basic premise of this research is that there are command languages for application systems. The methodology proposes ten steps, including acquiring knowledge for semantic analysis and usability enhancement. The tools consists of seven components which require domain knowledge and a dictionary for the relation between natural language and command language.

Experimental Evaluation on Associative Keyword Reminder by a Thesaurus

Abstract There is a need for search support as the amount of information on the network grows remarkably. Thesauri can be expected to suggest useful keywords for users search, however, their efficiency as keyword reminders is not well-known. This paper describes an experimental evaluation for clarifying the efficiency of thesauri as a term suggestion source, and gives consideration to the design guideline of the user interface when related terms are recommended by thesauri.