Online multi-user adaptive statistical machine translation

Prashant Mathur, Mauro Cettolo, Marcello Federico, José G.C. de Souza


Abstract
In this paper we investigate the problem of adapting a machine translation system to the feedback provided by multiple post-editors. It is well know that translators might have very different post-editing styles and that this variability hinders the application of online learning methods, which indeed assume a homogeneous source of adaptation data. We hence propose multi-task learning to leverage bias information from each single post-editors in order to constrain the evolution of the SMT system. A new framework for significance testing with sentence level metrics is described which shows that Multi-Task learning approaches outperforms existing online learning approaches, with significant gains of 1.24 and 1.88 TER score over a strong online adaptive baseline, on a test set of post-edits produced by four translators texts and on a popular benchmark with multiple references, respectively.
Anthology ID:
2014.amta-researchers.12
Volume:
Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track
Month:
October 22-26
Year:
2014
Address:
Vancouver, Canada
Editors:
Yaser Al-Onaizan, Michel Simard
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
152–165
Language:
URL:
https://aclanthology.org/2014.amta-researchers.12
DOI:
Bibkey:
Cite (ACL):
Prashant Mathur, Mauro Cettolo, Marcello Federico, and José G.C. de Souza. 2014. Online multi-user adaptive statistical machine translation. In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track, pages 152–165, Vancouver, Canada. Association for Machine Translation in the Americas.
Cite (Informal):
Online multi-user adaptive statistical machine translation (Mathur et al., AMTA 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.amta-researchers.12.pdf