Modularity in Inductively-Learned Word Pronunciation Systems

Explore this paper's citation graph

Summary

This work trains and test three word-pronunciation systems in which the number of abstraction levels (implemented as sequenced modules) is reduced from five, via three, to one, andalyses of empirical results indicate that positive utility effects of sequencing modules are outweighed by cascading errors passed on between modules.

Type
article
Published
1998-01-11
Cited by
14
References
36
Access
Open access

Keywords

Pronunciation, Computer science, Word (group theory), Natural language processing, Artificial intelligence

References

Cited by

Related papers