Syntactic and sub-lexical features for Turkish discriminative language models | IEEE Conference Publication | IEEE Xplore

Syntactic and sub-lexical features for Turkish discriminative language models


Abstract:

This paper investigates syntactic and sub-lexical features in Turkish discriminative language models (DLMs). DLM is a feature-based language modeling approach. It reranks...Show More

Abstract:

This paper investigates syntactic and sub-lexical features in Turkish discriminative language models (DLMs). DLM is a feature-based language modeling approach. It reranks the ASR output with discriminatively trained feature parameters. Syntactic information is incorporated into DLM as part-of-speech (PoS) tag n-gram features and head-to-head dependency relations. Sub-lexical units are first utilized as language modeling units in the baseline recognizer. Then, sub-lexical features are used to rerank the sub-lexical hypotheses. We explore features, similar to syntactic features, on sub-lexical units to reveal the implicit morpho-syntactic information conveyed by these units. We find out that DLM yields more improvement for sub-lexical units than for words. Basic sub-lexical n-gram features result in 0.6% reduction over the baseline and morpho-syntactic features yield an additional 0.4% reduction on the test set.
Date of Conference: 14-19 March 2010
Date Added to IEEE Xplore: 28 June 2010
ISBN Information:

ISSN Information:

Conference Location: Dallas, TX, USA
Electrical and Electronics Engineering Department, Bogazici University, Istanbul, Turkey
Electrical and Electronics Engineering Department, Bogazici University, Istanbul, Turkey
Center for Spoken Language Understanding, OGI/OHSU, Beaverton, OR, USA
OGI/OHSU, Center for Spoken Language Understanding, Beaverton, USA
Center for Spoken Language Understanding, OGI/OHSU, Beaverton, OR, USA
OGI/OHSU, Center for Spoken Language Understanding, Beaverton, USA

Electrical and Electronics Engineering Department, Bogazici University, Istanbul, Turkey
Electrical and Electronics Engineering Department, Bogazici University, Istanbul, Turkey
Center for Spoken Language Understanding, OGI/OHSU, Beaverton, OR, USA
OGI/OHSU, Center for Spoken Language Understanding, Beaverton, USA
Center for Spoken Language Understanding, OGI/OHSU, Beaverton, OR, USA
OGI/OHSU, Center for Spoken Language Understanding, Beaverton, USA

Contact IEEE to Subscribe

References

References is not available for this document.