Natural language parsing as statistical pattern recognition
Natural language parsing as statistical pattern recognition
A maximum entropy approach to natural language processing
Computational Linguistics
Controlling Content Realization with Functional Unification Grammars
Proceedings of the 6th International Workshop on Natural Language Generation: Aspects of Automated Natural Language Generation
JANUS-III: Speech-to-Speech Translation in Multiple Languages
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
A New Approach to Speech-Input Statistical Translation
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Trainable methods for surface natural language generation
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Generation that exploits corpus-based statistical knowledge
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
The correct place of lexical semantics in interlingual MT
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Natural language generation in the IBM flight information system
ANLP/NAACL-ConvSyst '00 Proceedings of the 2000 ANLP/NAACL Workshop on Conversational systems - Volume 3
Stochastic finite-state models for spoken language machine translation
NAACL-ANLP-EMTS '00 Proceedings of the 2000 NAACL-ANLP Workshop on Embedded machine translation systems - Volume 5
Phrase splicing and variable substitution using the IBM trainable speech synthesis system
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
High-quality speech-to-speech translation for computer-aided language learning
ACM Transactions on Speech and Language Processing (TSLP)
Two-Stage Hypotheses Generation for Spoken Language Translation
ACM Transactions on Asian Language Information Processing (TALIP)
IBM MASTOR system: multilingual automatic speech-to-speech translator
MST '06 Proceedings of the Workshop on Medical Speech Translation
A statistical semantic parser that integrates syntax and semantics
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
| Hi-index | 0.00 |
We present MARS (Multilingual Automatic tRanslation System), a research prototype speech-to-speech translation system. MARS is aimed at two-way conversational spoken language translation between English and Mandarin Chinese for limited domains, such as air travel reservations. In MARS, machine translation is embedded within a complex speech processing task, and the translation performance is highly effected by the performance of other components, such as the recognizer and semantic parser, etc. All components in the proposed system are statistically trained using an appropriate training corpus. The speech signal is first recognized by an automatic speech recognizer (ASR). Next, the ASR-transcribed text is analyzed by a semantic parser, which uses a statistical decision-tree model that does not require hand-crafted grammars or rules. Furthermore, the parser provides semantic information that helps further re-scoring of the speech recognition hypotheses. The semantic content extracted by the parser is formatted into a language-independent tree structure, which is used for an interlingua based translation. A Maximum Entropy based sentence-level natural language generation (NLG) approach is used to generate sentences in the target language from the semantic tree representations. Finally, the generated target sentence is synthesized into speech by a speech synthesizer.Many new features and innovations have been incorporated into MARS: the translation is based on understanding the meaning of the sentence; the semantic parser uses a statistical model and is trained from a semantically annotated corpus; the output of the semantic parser is used to select a more specific language model to refine the speech recognition performance; the NLG component uses a statistical model and is also trained from the same annotated corpus. These features give MARS the advantages of robustness to speech disfluencies and recognition errors, tighter integration of semantic information into speech recognition, and portability to new languages and domains. These advantages are verified by our experimental results.