Word Graphs for Statistical Machine Translation
Abstract:
Word graphs have various applications in the field of machine translation. Therefore it is important for machine translation systems to produce compact word graphs of high quality. We will describe the generation of word graphs for state of the art phrase-based statistical machine translation. We will use these word graph to provide an analysis of the search process. We will evaluate the quality of the word graphs using the well-known graph word error rate. Additionally, we introduce the two novel graph-to-string criteria: the position-independent graph word error rate and the graph BLEU score. Experimental results are presented for two Chinese–English tasks: the small IWSLT task and the NIST large data track task. For both tasks, we achieve significant reductions of the graph error rate already with compact word graphs. 1
Citations
| 62 | Finding consensus in speech recognition: Word error minimization and other applications of confusion networks – Mangu, Brill, et al. - 2000 |
| 23 | Translation with finite-state devices – Knight, Al-Onaizan - 1998 |
| 18 | Improvements in phrase-based statistical machine translation – Zens, Ney - 2004 |
| 17 | A finite-state approach to machine translation – Bangalore, Riccardi |
| 12 | Novel reordering approaches in phrase-based statistical machine translation – Kanthak, Vilar, et al. - 2005 |
| 10 | 2002. Generation of word graphs in statistical machine translation – Ueffing, Och, et al. |
| 4 | 2004. Overview of the IWSLT04 evaluation campaign – Akiba, Federico, et al. - 2004 |
| 2 | Bayes Decision Rules and Confidence Measures for Statistical – Ueffing, Ney - 2004 |
