Combinatory Examples Extraction for Machine Translation

Simões, Alberto Manuel; Almeida, José João

http://hdl.handle.net/10400.26/111

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
eamt06.pdf		118.09 KB	Adobe PDF	Download

Send Feedback

Authors

Simões, Alberto Manuel

Almeida, José João

Abstract(s)

One of the bottlenecks of example-based machine translation (EBMT) is to be able to amass automatically quantities of good examples. In our work in EBMT, we are investigating how far one can go by performing example extraction from parallel corpora using Probabilistic Translation Dictionaries to obtain example segmentation points. In fact, the success of EBMT highly depends on examples quality and quantity, but also in their length. Thus, we give special importance on methods to extract different size examples from the same translation unit. With this article we show that it is possible to extract quantities for examples from parallel corpora just using probabilistic translation dictionaries extracted from the same corpora

URI

http://hdl.handle.net/10400.26/111
http://www.linguateca.pt/superb/busca_publ.pl?idi=1146580911

Citation

Alberto Manuel Simões; José João Almeida. "Combinatory Examples Extraction for Machine Translation". In EAMT 11 th Annual Conference (Oslo, Norway, 19-20 June, 2006) , pp. 27-32