Abstract | ||
---|---|---|
We present the RWTH phrase-based statistical machine translation system designed for the translation of Arabic speech into English text. This system was used in the Global Autonomous Language Exploitation (GALE) Go/No-Go Translation Evaluation 2007.Using a two-pass approach, we first generate n-best translation candidates and then rerank these candidates using additional models. We give a short review of the decoder as well as of the models used in both passes.We stress the difficulties of spoken language translation, i.e. how to combine the recognition and translation systems and how to compensate for missing punctuation. In addition, we cover our work on domain adaptation for the applied language models. We present translation results for the official GALE 2006 evaluation set and the GALE 2007 development set. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/ASRU.2007.4430145 | ASRU |
Keywords | Field | DocType |
language translation,natural languages,speech recognition,statistical analysis,Arabic-to-English spoken language translation system,GALE 2007 development set,Global Autonomous Language Exploitation,RWTH phrase-based statistical machine translation system,applied language model,official GALE 2006 evaluation set,LM adaptation,adjustment of ASR and MT vocabularies,punctuation prediction,speech to text | Rule-based machine translation,Example-based machine translation,Language translation,Computer science,Evaluation of machine translation,Machine translation,Speech recognition,Machine translation software usability,Transfer-based machine translation,Natural language processing,Artificial intelligence,Computer-assisted translation | Conference |
Citations | PageRank | References |
15 | 0.72 | 13 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oliver Bender | 1 | 259 | 17.39 |
Evgeny Matusov | 2 | 466 | 38.01 |
Stefan Hahn | 3 | 113 | 9.36 |
Sasa Hasan | 4 | 245 | 17.35 |
Shahram Khadivi | 5 | 220 | 26.83 |
Hermann Ney | 6 | 14178 | 1506.93 |