Using Parsed Corpora for Estimating Stochastic Inversion Transduction Grammars

Germán Sanchis, Joan Andreu Sánchez


Abstract
An important problem when using Stochastic Inversion Transduction Grammars is their computational cost. More specifically, when dealing with corpora such as Europarl. only one iteration of the estimation algorithm becomes prohibitive. In this work, we apply a reduction of the cost by taking profit of the bracketing information in parsed corpora and show machine translation results obtained with a bracketed Europarl corpus, yielding interresting improvements when increasing the number of non-terminal symbols.
Anthology ID:
L08-1113
Volume:
Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)
Month:
May
Year:
2008
Address:
Marrakech, Morocco
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/465_paper.pdf
DOI:
Bibkey:
Cite (ACL):
Germán Sanchis and Joan Andreu Sánchez. 2008. Using Parsed Corpora for Estimating Stochastic Inversion Transduction Grammars. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).
Cite (Informal):
Using Parsed Corpora for Estimating Stochastic Inversion Transduction Grammars (Sanchis & Sánchez, LREC 2008)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/465_paper.pdf