Alert button
Picture for Masatoshi Fukui

Masatoshi Fukui

Alert button

PRIME: A System for Multi-lingual Patent Retrieval

Add code
Bookmark button
Alert button
Jun 24, 2002
Shigeto Higuchi, Masatoshi Fukui, Atsushi Fujii, Tetsuya Ishikawa

Figure 1 for PRIME: A System for Multi-lingual Patent Retrieval
Figure 2 for PRIME: A System for Multi-lingual Patent Retrieval

Given the growing number of patents filed in multiple countries, users are interested in retrieving patents across languages. We propose a multi-lingual patent retrieval system, which translates a user query into the target language, searches a multilingual database for patents relevant to the query, and improves the browsing efficiency by way of machine translation and clustering. Our system also extracts new translations from patent families consisting of comparable patents, to enhance the translation dictionary.

* Proceedings of MT Summit VIII, pp.163-167, Sep. 2001  
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

Applying a Hybrid Query Translation Method to Japanese/English Cross-Language Patent Retrieval

Add code
Bookmark button
Alert button
Jun 24, 2002
Masatoshi Fukui, Shigeto Higuchi, Youichi Nakatani, Masao Tanaka, Atsushi Fujii, Tetsuya Ishikawa

Figure 1 for Applying a Hybrid Query Translation Method to Japanese/English Cross-Language Patent Retrieval
Figure 2 for Applying a Hybrid Query Translation Method to Japanese/English Cross-Language Patent Retrieval
Figure 3 for Applying a Hybrid Query Translation Method to Japanese/English Cross-Language Patent Retrieval
Figure 4 for Applying a Hybrid Query Translation Method to Japanese/English Cross-Language Patent Retrieval

This paper applies an existing query translation method to cross-language patent retrieval. In our method, multiple dictionaries are used to derive all possible translations for an input query, and collocational statistics are used to resolve translation ambiguity. We used Japanese/English parallel patent abstracts to perform comparative experiments, where our method outperformed a simple dictionary-based query translation method, and achieved 76% of monolingual retrieval in terms of average precision.

* ACM SIGIR 2000 Workshop on Patent Retrieval, July, 2000  
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon