Generalized Stack Decoding . . .
Gespeichert in:
| Titel: | Generalized Stack Decoding . . . |
|---|---|
| Autoren: | Daniel Ortiz Martínez |
| Weitere Verfasser: | The Pennsylvania State University CiteSeerX Archives |
| Quelle: | http://www.statmt.org/wmt06/proceedings/pdf/WMT09.pdf. |
| Publikationsjahr: | 2006 |
| Bestand: | CiteSeerX |
| Beschreibung: | In this paper we propose a generalization of the Stack-based decoding paradigm for Statistical Machine Translation. The well known single and multi-stack decoding algorithms defined in the literature have been integrated within a new formalism which also defines a new family of stackbased decoders. These decoders allows a tradeoff to be made between the advantages of using only one or multiple stacks. The key point of the new formalism consists in parameterizeing the number of stacks to be used during the decoding process, and providing an efficient method to decide in which stack each partial hypothesis generated is to be insertedduring the search process. Experimental results are also reported for a search algorithm for phrase-based statistical translation models. |
| Publikationsart: | text |
| Dateibeschreibung: | application/pdf |
| Sprache: | English |
| Relation: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.5965; http://www.statmt.org/wmt06/proceedings/pdf/WMT09.pdf |
| Verfügbarkeit: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.5965 http://www.statmt.org/wmt06/proceedings/pdf/WMT09.pdf |
| Rights: | Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| Dokumentencode: | edsbas.983CADDB |
| Datenbank: | BASE |
Nájsť tento článok vo Web of Science | Abstract: | In this paper we propose a generalization of the Stack-based decoding paradigm for Statistical Machine Translation. The well known single and multi-stack decoding algorithms defined in the literature have been integrated within a new formalism which also defines a new family of stackbased decoders. These decoders allows a tradeoff to be made between the advantages of using only one or multiple stacks. The key point of the new formalism consists in parameterizeing the number of stacks to be used during the decoding process, and providing an efficient method to decide in which stack each partial hypothesis generated is to be insertedduring the search process. Experimental results are also reported for a search algorithm for phrase-based statistical translation models. |
|---|