Browse Prior Art Database

Adaptive Selection of Kanji or Kana in Kana-To-Kanji Conversion

IP.com Disclosure Number: IPCOM000061824D
Original Publication Date: 1986-Sep-01
Included in the Prior Art Database: 2005-Mar-09

Publishing Venue

IBM

Related People

Authors:
Ofuka, E Okochi, M [+details]

Abstract

This article describes a method to select adaptively Kanji (Chinese character) or Kana (Japanese syllabary) for particles in a Kana-to- Kanji conversion. Selection is based on (1) user's preference and (2) particle's position in a phrase, i.e. front or not. In Japanese texts, some particles may be written by either Kanji or Kana depending on (1) and (2) above. In order to automatically and adaptively select either one of Kanji and Kana in the Kana-to-Kanji conversion, a pair of four-bit Kanji levels KL(F) and KL(M) are introduced for each of the particles which can be written by Kanji. KL(F) is a Kanji level for use in the front of a phrase while KL(M) is for use in the middle or last thereof.