## Example-based decoding for statistical machine translation (2003)

Venue: | in Proc. of MT Summit IX |

Citations: | 6 - 2 self |

### BibTeX

@INPROCEEDINGS{Watanabe03example-baseddecoding,

author = {Taro Watanabe and Eiichiro Sumita},

title = {Example-based decoding for statistical machine translation},

booktitle = {in Proc. of MT Summit IX},

year = {2003},

pages = {410--417}

}

### OpenURL

### Abstract

This paper presents a decoder for statistical machine translation that can take advantage of the example-based machine translation framework. The decoder presented here is based on the greedy approach to the decoding problem, but the search is initiated from a similar translation extracted from a bilingual corpus. The experiments on multilingual translations showed that the proposed method was far superior to a word-by-word generation beam search algorithm. 1

### Citations

1472 | BLEU: a method for automatic evaluation of machine translation
- Papineni, Roukos, et al.
- 2002
(Show Context)
Citation Context ... which penalizes without considering positional disfluencies (Och and Ney, 2002). BLEU: BLEU score, which computes the ratio of the n-gram for the translation results found in reference translations (=-=Papineni et al., 2002-=-). Contrary to the above error metrics, the higher scores indicates better translations. SE: Subjective evaluation ranks ranging from A to D (A : perfect, B : fair, C : acceptable and D : nonsense), j... |

1173 | The mathematics of statistical machine translation: Parameter estimation
- Brown, Pietra, et al.
- 1994
(Show Context)
Citation Context ...tatistical machine translation formulates the problem of translating a sentence in a language J into another language E as the maximization problem of the conditional probability Ê = argmax E P(E|J) (=-=Brown et al., 1993-=-). The application of the Bayes Rule resulted in Ê = argmax E P(E)P(J|E). The former term P(E) is called a language model, representing the likelihood of E. The latter term P(J|E) is called a translat... |

367 | Ney (2002), Discriminative training and maximum entropy models for statistical machine translation
- Och, Hermann
(Show Context)
Citation Context ... Watanabe and Sumita (2002). The metrics for this evaluation were as follows: WER: Word-error-rate, which penalizes the edit distance (insertion/deletion/substitution) against reference translations (=-=Och and Ney, 2002-=-). PER: Position independent WER, which penalizes without considering positional disfluencies (Och and Ney, 2002). BLEU: BLEU score, which computes the ratio of the n-gram for the translation results ... |

242 |
A framework of a mechanical translation between Japanese and English by analogy principle
- Nagao
- 1984
(Show Context)
Citation Context ...earch decoding algorithm was often stuck into sub-optimal solutions. This paper presents an example-based decoding algorithm, an approach to merging statistical and example-based machine translation (=-=Nagao, 1984-=-). 1 The source/target sentences are the channel model’s source/target that correspond to the translation system’s output/input. E= NULL0 show1 me2 the3 one4 in5 the6 window7 J= uindo1 no2 shinamono3 ... |

179 | A phrase-based, joint probability model for statistical machine translation - D, Wong - 2002 |

112 | Fast decoding and optimal decoding for machine translation
- Germann, Jahr, et al.
- 2001
(Show Context)
Citation Context ...ligned to NULL and A j= 0. When the fertility of EA j becomes zero, then the word EA j is removed. e is selected from among the translation candidates, computed from the inverse of the Lexicon Model (=-=Germann et al., 2001-=-). • Translate and insert words: Perform the translation of a word, and insert a sequence of zero fertility words at appropriate positions. The candidate sequence of zero fertility words is selected f... |

78 |
Toward a Broad-coverage Bilingual Corpus for Speech Translation of Travel Conversation in the Real World
- Takezawa, Sumita, et al.
- 2002
(Show Context)
Citation Context ...lignments. 4 Evaluation 4.1 Corpus The corpus for this experiment was extracted from the Basic Travel Expression Corpus (BTEC), a collection of travel conversational phrases for Japanese and English (=-=Takezawa et al., 2002-=-). The corpus was extended to other languages, Korean and Chinese, as illustrated in Table 1. The entire corpus was split into three parts, 152,169 sentences for training, 4,846 sentences for testing,... |

35 | Automated Generalization of Translation Examples - Brown - 2000 |

20 | Towards a unified approach to memory- and statistical-based machine translation - Marcu - 2001 |

18 | Word re-ordering and dp-based search in statistical machine translation - Tillmann, Ney - 2000 |

12 | Overcoming the customization bottleneck using example-based mt - Richardson, Dolan, et al. - 2001 |

11 | Iterative, DPBased Search Algorithm For Statistical
- Garcia-Varea, Ney
- 1998
(Show Context)
Citation Context ...00). Due to its complexity, many pruning strategies have to be introduced, such as beam pruning (Och et al., 2001), fertility pruning (Watanabe and Sumita, 2002) or word-for-word translation pruning (=-=García-Vaera et al., 1998-=-), so that the search system can output results in a reasonable time. However, search errors become inevitable under the restricted search space. As Akiba et al. (2002) pointed out, though there exist... |

10 | Example-based machine translation using DP-matching between word sequences - Sumita |

5 | Bidirectional decoding for statistical machine translation
- Watanabe, Sumita
- 2002
(Show Context)
Citation Context ...y-word beam search algorithm as presented by Tillmann and Ney (2000). Due to its complexity, many pruning strategies have to be introduced, such as beam pruning (Och et al., 2001), fertility pruning (=-=Watanabe and Sumita, 2002-=-) or word-for-word translation pruning (García-Vaera et al., 1998), so that the search system can output results in a reasonable time. However, search errors become inevitable under the restricted sea... |

3 | Translating with examples - Way - 2001 |

2 | A transfer system using example-based approach - Watanabe, Maruyama - 1994 |