An efficient method of intention understanding and learning for the ambiguous expressions of sentence end
by Nobuo Suzuki, Kazuhiko Tsuda
International Journal of Computer Applications in Technology (IJCAT), Vol. 33, No. 2/3, 2008

Abstract: In recent years, the usage of Internet and mobile phone has increased explosively and individuals have many more opportunities to send out information over these networks. Considering this media, the styles of writing tend to be more colloquial, where users commonly utilise peculiar expressions such as emoticons, pictograms, three-point leaders and 'taigen-dome' (a Japanese method that ends a sentence with a noun). Although these expressions do not clearly indicate the intentions of the writers, they would be very useful when we understand the intentions and emotions hidden within sentences. And we can use these expressions for recognising emotions efficiently. By focusing on Japanese versions of emoticons and three-point leaders, this paper proposes a method to presume the writers' intentions using the rules extracted from corpora built from data on the Internet. The evaluation tests conducted have produced excellent results for both emoticons and three-point leaders. We also mention reasons of the experimental errors of the rules for emoticons and describe the aspect of the rules for three-point-leaders such as limiting the meaning.

Online publication date: Wed, 10-Dec-2008

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com