Difference between revisions of "Koehn et al, ACL 2003"
From Cohen Courses
Jump to navigationJump to search| Line 1: | Line 1: | ||
Being edited by Rui Correia | Being edited by Rui Correia | ||
| − | + | ||
| + | |||
| + | == Citation == | ||
| + | Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase-based translation. In Proceedings of HLT-NAACL 2003, pages 127–133. [http://www.aclweb.org/anthology-new/N/N03/N03-1017.pdf] | ||
| + | |||
| + | == Summary == | ||
| + | |||
| + | In this [[Category::paper]] the authors [[AddressesProblem::Machine Translation]] | ||
| + | |||
| + | == Evaluation Framework == | ||
| + | |||
| + | == Methods for Learning Phrase Translation == | ||
| + | [[RelatedPaper::Vogal et al, COLING 1996]] | ||
| + | |||
| + | <math> | ||
| + | \max_{0 \le z \le 1} \sum_{jk \in \varepsilon}{s_{jk} z_{jk}} + \sum_{jklm \in Q}{s_{jklm}z_{jklm}} | ||
| + | </math> | ||
| + | |||
| + | <math> | ||
| + | s.t. \sum _{j \in V^s} z_{jk} \le 1, \forall k \in V^t; | ||
| + | </math> | ||
| + | |||
| + | <math> | ||
| + | \sum _{k \in V^t} z_{jk} \le 1, \forall j \in V^s; | ||
| + | </math> | ||
| + | |||
| + | <math> | ||
| + | z_{jklm} \le z_{jk}, z_{jklm} \le z_{lm}, \forall jklm \in Q, | ||
| + | </math> | ||
| + | |||
| + | |||
| + | == Experimental Results == | ||
| + | The authors used the [[UsesDataset::Hansards]] | ||
| + | [[File:Lacostejulienresults.png|300px]] | ||
Revision as of 17:47, 28 November 2011
Being edited by Rui Correia
Contents
Citation
Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase-based translation. In Proceedings of HLT-NAACL 2003, pages 127–133. [1]
Summary
In this paper the authors Machine Translation
Evaluation Framework
Methods for Learning Phrase Translation
Experimental Results
The authors used the Hansards
