Advances in syntax-based Malay-English speech translation

In this paper, we present advanced techniques that improved the performance of IBM Malay-English speech translation system significantly. During this work, we generated linguistics-driven hierarchical rules to enhance the formal syntax-based translation model; designed an active learning approach wi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2009 IEEE International Conference on Acoustics, Speech and Signal Processing s. 4801 - 4804
Hlavní autoři: Bing Xiang, Bowen Zhou, Cmejrek, M.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.04.2009
Témata:
Active Learning
Automatic speech recognition
Bidirectional control
Data mining
Humans
Machine learning
Machine Translation
Natural languages
Semisupervised learning
Speech recognition
Tagging
Training data
ISBN:9781424423538, 1424423538
ISSN:1520-6149
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we present advanced techniques that improved the performance of IBM Malay-English speech translation system significantly. During this work, we generated linguistics-driven hierarchical rules to enhance the formal syntax-based translation model; designed an active learning approach with bi-directional translations that outperformed unsupervised training; utilized translation direction information in parallel training corpus to build direction-specific interpolated language models for machine translation. There is 20% relative improvement achieved in the translation performance through all these techniques. A state-of-the-art Malay speech recognition system was also established as one of the crucial modules in the rapidly developed Malay-English speech translation.
ISBN:9781424423538
1424423538
ISSN:1520-6149
DOI:10.1109/ICASSP.2009.4960705