Computing multiple weighted reordering hypotheses for a phrase-based statistical machine translation system
Marta
R
Costa-Jussà
author
José
A
R
Fonollosa
author
2008-oct 21-25
text
Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Research Papers
Association for Machine Translation in the Americas
Waikiki, USA
conference publication
Reordering is one source of error in statistical machine translation (SMT). This paper extends the study of the statistical machine reordering (SMR) approach, which uses the powerful techniques of the SMT systems to solve reordering problems. Here, the novelties yield in: (1) using the SMR approach in a SMT phrase-based system, (2) adding a feature function in the SMR step, and (3) analyzing the reordering hypotheses at several stages. Coherent improvements are reported in the TC-STAR task (Es/En) at a relatively low computational cost.
costa-jussa-fonollosa-2008-computing
https://aclanthology.org/2008.amta-papers.6
2008-oct 21-25
82
88