Syntactic and sub-lexical features for Turkish discriminative language models


Arisoy E., SARAÇLAR M., Roark B., Shafran I.

2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010, Dallas, TX, Amerika Birleşik Devletleri, 14 - 19 Mart 2010, ss.5538-5541, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/icassp.2010.5495226
  • Basıldığı Şehir: Dallas, TX
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.5538-5541
  • Anahtar Kelimeler: language modeling, automatic speech recognition, discriminative training, sub-lexical recognition units
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

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. ©2010 IEEE.