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
Document File: 2 page(s) / 40K

Publishing Venue

IBM

Related People

Ofuka, E: AUTHOR [+2]

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.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 52% of the total text.

Page 1 of 2

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

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. They are generally expressed as follows: KL(p) = 'xyzz'b (b:binary) p = F or M The first half 'xy' represents usage history in a session as follows: '00' = Use standard level. '01' = Kanji was used. '10' = Kana was used. 'xy' is initially set to '00'. The second half 'zz' represents a standard level as follows: '00' (level 0) = Use Kana. '01' (level 1) = Prefer Kana to Kanji with some variation by individuals. '10' (level 2) = Prefer Kanji to Kana with some variation by individuals. '11' (level 3) = Use Kanji The second half 'zz' should be initially prepared as illustrated in the figure. Each underline in the figure designates a unit of particle. When Kanji or Kana is to be selected for a particle, a corresponding KL(p) is treated as a decimal integer with 'x' being a sign (x=1 means negative, while x=0 means positive), and compared with a general Kanji-...