The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Japanese word prediction

Author

  • Fredrik Lindh

Summary, in English

This report deals with the implementation of a Japanese word prediction engine written by the author. As this type of software does not seem to exist for Japanese at the time of writing, it could prove useful in Japanese augmentative and alternative communication (AAC) as a software tool used to improve typing speed and reduce the amount of keystrokes needed to produce text. Word prediction, in contrast to the word
completion software commonly found in mobile phones and word processor intellisense engines etc. is a technique for suggesting a followup word after a word has just been completed. This is usually done by providing a list of the most probable words to the user, sorted by commonality (general and user-specific frequency). Combined with good word completion software and a responsive user interface, word prediction is one of the most powerful assistive tools available to movement impaired users today.
The main goals of the thesis will be to:
1. Answer as many of the questions raised by the language differences as possible.
2. Investigate further avenues of research in the subject.
3. Make a functional word prediction prototype for Japanese.
All project code is in the public domain and is currently hosted at:
http://www.mediafire.com/?rrhqtqsgp6ei6m3

Department/s

Publishing year

2011

Language

English

Document type

Student publication for Bachelor's degree

Topic

  • Languages and Literatures

Supervisor

  • Lars Larm