The RWTH System for Statistical Translation of Spoken Dialogues

This paper gives an overview of our work on statistical machine translation of spoken dialogues, in particular in the framework of the VERBMOBIL project. The goal of the VERBMOBIL project is the translation of spoken dialogues in the domains of appointment scheduling and travel planning. Starting with the Bayes decision rule as in speech recognition, we show how the required probability distributions can be structured into three parts: the language model, the alignment model and the lexicon model. We describe the components of the system and report results on the VERBMOBIL task. The experience obtained in the VERBMOBIL project, in particular a large-scale end-to-end evaluation, showed that the statistical approach resulted in significantly lower error rates than three competing translation approaches: the sentence error rate was 29% in comparison with 52% to 62% for the other translation approaches.

[1]  Hermann Ney,et al.  A DP based Search Algorithm for Statistical Machine Translation , 1998, ACL.

[2]  Hermann Ney,et al.  Translation with Cascaded Finite State Transducers , 2000, ACL.

[3]  Hermann Ney,et al.  On the Use of Grammar Based Language Models for Statistical Machine Translation , 2000, IWPT.

[4]  Peter Poller,et al.  The Verbmobil Generation Component VM-GECO , 2000 .

[5]  Hermann Ney,et al.  A Comparison of Alignment Models for Statistical Machine Translation , 2000, COLING.

[6]  Marko Auerswald.  Example-Based Machine Translation with Templates , 2000 .

[7]  Franz Josef Och,et al.  An Efficient Method for Determining Bilingual Word Classes , 1999, EACL.

[8]  Wolfgang Wahlster,et al.  Verbmobil: Foundations of Speech-to-Speech Translation , 2000, Artificial Intelligence.

[9]  Robert L. Mercer,et al.  The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[10]  Günther Görz,et al.  Processing Self Corrections in a speech to speech system , 2000, COLING.

[11]  Hermann Ney,et al.  HMM-Based Word Alignment in Statistical Translation , 1996, COLING.

[12]  Hermann Ney,et al.  Word Re-ordering and DP-based Search in Statistical Machine Translation , 2000, COLING.

[13]  Hermann Ney,et al.  A DP based Search Using Monotone Alignments in Statistical Translation , 1997, ACL.

[14]  Hermann Ney,et al.  Improving SMT quality with morpho-syntactic analysis , 2000, COLING.

[15]  Martin C. Emele,et al.  Semantic-based Transfer , 1996, COLING.

[16]  Noam Chomsky.  Quine’s Empirical Assumptions , 1968 .

[17]  Hermann Ney,et al.  Algorithms for statistical translation of spoken language , 2000, IEEE Trans. Speech Audio Process..

[18]  Hermann Ney,et al.  Improved Alignment Models for Statistical Machine Translation , 1999, EMNLP.

[19]  Hermann Ney,et al.  An Evaluation Tool for Machine Translation: Fast Evaluation for MT Research , 2000, LREC.

[20]  Hans Uszkoreit,et al.  Deep Linguistic Analysis with HPSG , 2000 .

[21]  Jaakko Hintikka,et al.  Words And Objections , 1969 .

[22]  Walther von Hahn,et al.  Functional Validation of a Machine Interpretation System: Verbmobil , 2000 .

[23]  John D. Lafferty,et al.  The Candide System for Machine Translation , 1994, HLT.

[24]  Norbert Reithinger,et al.  Robust Content Extraction for Translation and Dialog Processing , 2000 .