Processing highly variant language using incremental model selection

Explore this paper's citation graph

Summary

This dissertation provides an architecture for NLP that allows for better handling of complicated language variation and finds that segmenting language before tagging, and then applying single-language homogeneous language models, is competitive to multilingual heterogeneous tagging models.

Type
article
Published
2012-01-01
Cited by
9
References
93

Keywords

Computer science, Artificial intelligence, Speech recognition, Natural language processing, Pattern recognition (psychology)

References

Cited by

Related papers