The EuTrans Spoken Language Translation System
2000
The EuTransAll project aims at using example-based approaches for the automatic development of Machine Translation systems accepting text and speech input for limited-domain applications. During the first phase of the project, a speech-translation system that is based on the use of automatically learned subsequential transducers has been built. This paper contains a detailed and mostly self-contained overview of the transducer-learning algorithms and system architecture, along with a new approach for using categories representing words or short phrases in both input and output languages. Experimental results using this approach are reported for a task involving the recognition and translation of sentences in the hotel-reception communication domain, with a vocabulary of 683 words in Spanish. A translation word-error rate of 1.97% is achieved in real-time factor 2.7 on a Personal Computer.
Keywords:
- Linguistics
- Computer-assisted translation
- Artificial intelligence
- Machine translation
- Natural language processing
- Speech translation
- Computer science
- Example-based machine translation
- Speech recognition
- Word error rate
- Transfer-based machine translation
- Rule-based machine translation
- Vocabulary
- personal computer
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
28
References
46
Citations
NaN
KQI