Language model adaptation with MAP estimation and the perceptron algorithm
2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics - Short Papers, HLT-NAACL 2004, Massachusetts, Amerika Birleşik Devletleri, 2 - 07 Mayıs 2004, ss.21-24, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Basıldığı Şehir: Massachusetts
- Basıldığı Ülke: Amerika Birleşik Devletleri
- Sayfa Sayıları: ss.21-24
- Boğaziçi Üniversitesi Adresli: Evet
Özet
In this paper, we contrast two language model adaptation approaches: MAP estimation and the perceptron algorithm. Used in isolation, we show that MAP estimation outperforms the latter approach, for reasons which argue for combining the two approaches. When combined, the resulting system provides a 0.7 percent absolute reduction in word error rate over MAP estimation alone. In addition, we demonstrate that, in a multi-pass recognition scenario, it is better to use the perceptron algorithm on early pass word lattices, since the improved error rate improves acoustic model adaptation.