DocumentCode :
3255681
Title :
An incremental concept formation approach to acquisition of anaphoric regularity in Mandarin Chinese
Author :
Chen, Benjamin L. ; Soo, Von-Wun
Author_Institution :
Comput. & Commun. Res. Labs., Ind. Technol. Res. Inst., Hsinchu, Taiwan
fYear :
1992
fDate :
28-30 May 1992
Firstpage :
278
Lastpage :
281
Abstract :
A modified version of the incremental learning model of Lebowitz´s UNIMEM (1986) is proposed. This new model is called G-UNIMEM which is motivated from natural language acquisition study. It can extract causal relations from a set of training instances annotated with specified cause and goal features. The experiment is carried out on the acquisition of anaphoric regularity in Mandarin Chinese
Keywords :
learning (artificial intelligence); learning systems; natural languages; G-UNIMEM; Mandarin Chinese; anaphoric regularity acquisition; causal relations extraction; cause features; goal features; incremental learning model; natural language acquisition; training instances; Application software; Communication industry; Computer applications; Computer industry; Computer science; Electronic mail; Learning systems; Machine learning; Natural languages; Research and development;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computing and Information, 1992. Proceedings. ICCI '92., Fourth International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-8186-2812-X
Type :
conf
DOI :
10.1109/ICCI.1992.227655
Filename :
227655
Link To Document :
بازگشت