Head automata for speech translation

Author

Alshawi, Hiyan

Author_Institution

AT&T Bell Labs., Murray Hill, NJ, USA

Volume

4

fYear

1996

fDate

3-6 Oct 1996

Firstpage

2360

Abstract

Presents statistical language and translation models based on collections of small finite-state machines that we call “head automata”. The models are intended to capture the lexical sensitivity of N-gram models and direct statistical translation models, while at the same time taking account of the hierarchical phrasal structure of language. Two types of head automata are defined: relational head automata, which are suitable for translation by the transfer of dependency trees, and head transducers, which are suitable for direct recursive lexical translation

Keywords

computational linguistics; finite state machines; grammars; language translation; nomograms; speech processing; statistics; trees (mathematics); N-gram models; dependency tree transfer; direct recursive lexical translation; direct statistical translation models; finite-state machines; head transducers; hierarchical phrasal structure; lexical sensitivity; relational head automata; speech translation; statistical language models; Automata; Automatic programming; Context modeling; Functional programming; Magnetic heads; Natural languages; Robustness; Speech; Stochastic processes; Transducers;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607282

Filename

607282