## A Systematic Comparison of Various Statistical Alignment Models (2003)

### Cached

### Download Links

- [acl.ldc.upenn.edu]
- [www.aclweb.org]
- [www.aclweb.org]
- [aclweb.org]
- [wing.comp.nus.edu.sg]
- [aclweb.org]
- [ucrel.lancs.ac.uk]
- [www-rohan.sdsu.edu]
- [www.mt-archive.info]
- DBLP

### Other Repositories/Bibliography

Venue: | Computational Linguistics |

Citations: | 1253 - 58 self |

### BibTeX

@ARTICLE{Och03asystematic,

author = {Franz Josef Och and Hermann Ney and Franz Josef and Och Hermann Ney},

title = {A Systematic Comparison of Various Statistical Alignment Models},

journal = {Computational Linguistics},

year = {2003},

volume = {29}

}

### Years of Citing Articles

### OpenURL

### Abstract

this article the problem of finding the word alignment of a bilingual sentence-aligned corpus by using language-independent statistical methods. There is a vast literature on this topic, and many different systems have been suggested to solve this problem. Our work follows and extends the methods introduced by Brown, Della Pietra, Della Pietra, and Mercer (1993) by using refined statistical models for the translation process. The basic idea of this approach is to develop a model of the translation process with the word alignment as a hidden variable of this process, to apply statistical estimation theory to compute the "optimal" model parameters, and to perform alignment search to compute the best word alignment

### Citations

8084 | Maximum likelihood from incomplete data via the EM algorithm - Dempster, Laird, et al. - 1977 |

512 |
An inequality and associated maximization technique in statistical estimation of probabilistic functions of a markov process
- Baum
- 1972
(Show Context)
Citation Context ... = {{p(f | e)}, {p=1(∆j |···)}, {p>1(∆j |···)}, {p(φ | e)}, p1} (34) To train the model parameters θ, we use a maximum-likelihood approach, as described in equation (4), by applying the EM algorithm (=-=Baum 1972-=-). The different models are trained in succession on the same data; the final parameter values of a simpler model serve as the starting point for a more complex model. In the E-step of Model 1, the le... |

292 |
Measures of the Amount of Ecologic Association Between Species
- Dice
- 1945
(Show Context)
Citation Context ...use a function of the similarity between the types of the two languages (Smadja, McKeown, and Hatzivassiloglou 1996; Ker and Chang 1997; Melamed 2000). Frequently, variations of the Dice coefficient (=-=Dice 1945-=-) are used as this similarity function. For each sentence pair, a matrix including the association scores between every word at every position is then obtained: dice(i, j) = 2 · C(ei, fj) C(ei) · C(fj... |

271 | A Comparison of Alignment Models for Statistical Machine Translation
- Och
- 2000
(Show Context)
Citation Context ...data sparseness problem. 1.2 Applications There are numerous applications for word alignments in natural language processing. These applications crucially depend on the quality of the word alignment (=-=Och and Ney 2000-=-; Yarowsky and Wicentowski 2000). An obvious application for word alignment methods is the automatic extraction of bilingual lexica and terminology from corpora (Smadja, McKeown, and Hatzivassiloglou ... |

143 | 2000), Models of translational equivalence among words, Computational Linguistics 26(2):221–249
- Melamed
(Show Context)
Citation Context ...wsky and Wicentowski 2000). An obvious application for word alignment methods is the automatic extraction of bilingual lexica and terminology from corpora (Smadja, McKeown, and Hatzivassiloglou 1996; =-=Melamed 2000-=-). Statistical alignment models are often the basis of single-word-based statistical machine translation systems (Berger et al. 1994; Wu 1996; Wang and Waibel 1998; Nießen et al. 1998; García-Varea, C... |

141 | Translating Collocations for Bilingual Lexicons: A Statistical Approach - Smadja, McKeown, et al. - 1996 |

135 | editor. VERBMOBIL: Foundations of Speech-to-Speech Translation - Wahlster - 2000 |

114 | Decoding complexity in word replacement translation models - Knight - 1999 |

105 | Using cognates to align sentences in bilingual corpora - Simard, Foster, et al. - 1992 |

100 | Improved Clustering Techniques for Class-based Statistical Language Modelling - Kneser, Ney |

84 | A Polynomial-Time Algorithm for Statistical Machine Translation
- Wu
- 1996
(Show Context)
Citation Context ... corpora (Smadja, McKeown, and Hatzivassiloglou 1996; Melamed 2000). Statistical alignment models are often the basis of single-word-based statistical machine translation systems (Berger et al. 1994; =-=Wu 1996-=-; Wang and Waibel 1998; Nießen et al. 1998; García-Varea, Casacuberta, and Ney 1998; Och, Ueffing, and Ney 2001; Germann et al. 2001). In addition, these models are the starting point for refined phra... |

51 | The Candide system for machine translation
- Berger, Brown, et al.
- 1994
(Show Context)
Citation Context ...and terminology from corpora (Smadja, McKeown, and Hatzivassiloglou 1996; Melamed 2000). Statistical alignment models are often the basis of single-word-based statistical machine translation systems (=-=Berger et al. 1994-=-; Wu 1996; Wang and Waibel 1998; Nießen et al. 1998; García-Varea, Casacuberta, and Ney 1998; Och, Ueffing, and Ney 2001; Germann et al. 2001). In addition, these models are the starting point for ref... |

45 | Inducing multilingual text analysis tools via robust projection across aligned corpora - YAROWSKY, NGAI, et al. |

44 | Automated Dictionary Extraction for “Knowledge-Free” Example-Based Translation
- Brown
- 1997
(Show Context)
Citation Context ...01; Germann et al. 2001). In addition, these models are the starting point for refined phrase-based statistical (Och and Weber 1998; Och, Tillmann, and Ney 1999) or example-based translation systems (=-=Brown 1997-=-). In such systems, the quality of the machine translation output directly depends on the quality of the initial word alignment (Och and Ney 2000). 21Computational Linguistics Volume 29, Number 1 Ano... |

42 | Manual annotation of translational equivalence: The Blinker project
- Melamed
- 1998
(Show Context)
Citation Context ...present an annotation scheme for single-word-based alignments and a corresponding evaluation criterion. It is well known that manually performing a word alignment is a complicated and ambiguous task (=-=Melamed 1998-=-). Therefore, in performing the alignments for the research presented here, we use an annotation scheme that explicitly allows for ambiguous alignments. The persons conducting the annotation are asked... |

34 |
Algorithms for statistical translation of spoken language
- Ney, Nießen, et al.
- 2000
(Show Context)
Citation Context ...o those studied in this article have been used as a starting point for refined phrase-based statistical machine translation systems (Alshawi, Bangalore, and Douglas 1998; Och, Tillmann, and Ney 1999; =-=Ney et al. 2000-=-). In Och and Ney (2000), the overall result of the experimental evaluation has been that an improved alignment quality yields an improved subjective quality of the statistical machine translation sys... |

30 | A Class-Based Approach to Word Alignment
- Ker, Chang
- 1997
(Show Context)
Citation Context ...ced through corpus preprocessing steps that perform grouping and splitting of words. Some papers report improvements in the alignment quality of statistical methods when linguistic knowledge is used (=-=Ker and Chang 1997-=-; Huang and Choi 2000). In these methods, the linguistic knowledge is used mainly to filter out incorrect alignments. In this work, we shall avoid making explicit assumptions concerning the language u... |

30 | A DP-based search algorithm for statistical machine translation
- Niessen, Vogel, et al.
- 1998
(Show Context)
Citation Context ...Hatzivassiloglou 1996; Melamed 2000). Statistical alignment models are often the basis of single-word-based statistical machine translation systems (Berger et al. 1994; Wu 1996; Wang and Waibel 1998; =-=Nießen et al. 1998-=-; García-Varea, Casacuberta, and Ney 1998; Och, Ueffing, and Ney 2001; Germann et al. 2001). In addition, these models are the starting point for refined phrase-based statistical (Och and Weber 1998; ... |

29 | But dictionaries are data too - Brown, Pietra, et al. - 1993 |

27 | An efficient A* search algorithm for statistical machine translation - Och, Ueffing, et al. - 2001 |

25 | Automatic acquisition of hierarchical transduction models for machine translation - Alshawi, Bangalore, et al. - 1998 |

15 | Giza++: Training of statistical translation models. available at http://www.fjoch.com/GIZA++.html - Och, Ney - 2000 |

13 | Improving statistical natural language translation with categories and rules
- Och, Weber
- 1998
(Show Context)
Citation Context ...; Nießen et al. 1998; García-Varea, Casacuberta, and Ney 1998; Och, Ueffing, and Ney 2001; Germann et al. 2001). In addition, these models are the starting point for refined phrase-based statistical (=-=Och and Weber 1998-=-; Och, Tillmann, and Ney 1999) or example-based translation systems (Brown 1997). In such systems, the quality of the machine translation output directly depends on the quality of the initial word ali... |

11 | Iterative, DPBased Search Algorithm For Statistical - Garcia-Varea, Ney - 1998 |

10 | Fast decoding for statistical machine translation
- Wang, Waibel
- 1998
(Show Context)
Citation Context ...(Smadja, McKeown, and Hatzivassiloglou 1996; Melamed 2000). Statistical alignment models are often the basis of single-word-based statistical machine translation systems (Berger et al. 1994; Wu 1996; =-=Wang and Waibel 1998-=-; Nießen et al. 1998; García-Varea, Casacuberta, and Ney 1998; Och, Ueffing, and Ney 2001; Germann et al. 2001). In addition, these models are the starting point for refined phrase-based statistical (... |

7 | decoding and optimal decoding for machine translation - Fast |

4 | A statistical MT tutorial workbook. Available at: http://www.isi.edu/∼knight - Knight - 1999 |

2 | A Systematic Comparison of Statistical Alignment Models - Och, Ney - 2003 |

1 | 49 Linguistics Volume 29, Number 1 - Dagan, Church - 1993 |

1 | 50 and Ney Comparison of Statistical Alignment Models - Vogel, Ney, et al. - 1996 |

1 | An iterative, DP-based search algorithm for statistical machine translation - a-Varea, Ismael, et al. - 1998 |