Utilizing a Phrase Translation Table and Portion of Patent Families with No Parallel Sentences Extracted in Estimating Translation of Technical Terms

• Itsuki Toyota

  Graduate School of Systems and Information Engineering, University of Tsukuba

• Zi Long

  Graduate School of Systems and Information Engineering, University of Tsukuba

• Lijuan Dong

  Graduate School of Systems and Information Engineering, University of Tsukuba

• Takehito Utsuro

  Faculty of Engineering, Information and Systems, University of Tsukuba

• Mikio Yamamoto

  Faculty of Engineering, Information and Systems, University of Tsukuba

Bibliographic Information

Other Title

• パテントファミリーを用いた専門用語訳語獲得における対訳文対非抽出部分およびフレーズテーブルの利用

Abstract

In the previous methods of generating bilingual lexicon from parallel patent sentences extracted from patent families, the portion from which parallel patent sentences are extracted is about 30% out of the whole "Background" and "Embodiment" parts and about 70% are not used. Considering this situation, this paper proposes to generate bilingual lexicon for technical terms not only from the 30% but also from the remaining 70% out of the whole "Background" and "Embodiment" parts. The proposed method employs the compositional translation estimation technique utilizing the remaining 70% as a comparable corpus for validating translation candidates. As the bilingual constituent lexicons in compositional translation, we use an existing bilingual lexicon as well as the phrase translation table trained with the parallel patent sentences extracted from the 30%. Finally, we show that about 7,300 technical term translation pairs can be acquired from 1,000 patent families.

Journal

• IPSJ SIG Notes

  IPSJ SIG Notes 2013 (12), 1-8, 2013-07-11

  Information Processing Society of Japan (IPSJ)

Keywords

• 機械翻訳

Details

• CRID: 1573387452695535360
• NII Article ID: 110009586063
• NII Book ID: AN10115061
• Text Lang: ja
• Data Source:
  • CiNii Articles