Browse Prior Art Database

Method for Detection of Phrase Boundaries

IP.com Disclosure Number: IPCOM000040591D
Original Publication Date: 1987-Dec-01
Included in the Prior Art Database: 2005-Feb-02
Document File: 2 page(s) / 33K

Publishing Venue

IBM

Related People

Siio, I: AUTHOR

Abstract

This article describes a user interface method for designating phrase boundaries by changing typing speed while entering text to an on-line system. Japanese word processors commonly use Kana to Kanji conversion facilities for entering text containing Kanji characters. Conventional Kana to Kanji conversion facilities are basically designed to convert a Kana string into a Kana-Kanji mixed string for each phrase. Recently, multiple-phrase Kana to Kanji conversion has been widely used, which determines phrase boundaries in a Kana string by a grammatical analysis and then converts the Kana string into a Kana-Kanji string for each phrase. However, a grammatical analysis can generate more than one result because of the grammatical ambiguity of the Kana string.

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 78% of the total text.

Page 1 of 2

Method for Detection of Phrase Boundaries

This article describes a user interface method for designating phrase boundaries by changing typing speed while entering text to an on-line system. Japanese word processors commonly use Kana to Kanji conversion facilities for entering text containing Kanji characters. Conventional Kana to Kanji conversion facilities are basically designed to convert a Kana string into a Kana-Kanji mixed string for each phrase. Recently, multiple-phrase Kana to Kanji conversion has been widely used, which determines phrase boundaries in a Kana string by a grammatical analysis and then converts the Kana string into a Kana-Kanji string for each phrase. However, a grammatical analysis can generate more than one result because of the grammatical ambiguity of the Kana string. This method is used together with the grammatical analysis to select the most likely candidate for each phrase boundary, and relies on the rationale that typing tends to become slower at phrase boundaries because a user needs more time for mentally preparing the next phrase. Referring now to the drawing, which shows a Japanese multiple - phrase Kana to Kanji conversion system using this method together with a conventional grammatical analysis, a signal from the Keyboard 1 is provided to the key entry processing routine 2, which then generates key-code information and keystroke-interval information. Every keystroke-interval is measured by the timer routine 3. The key-code i...