Improving MEANT based semantically tuned SMT

Meriem Beloucif, Chi-kiu Lo, Dekai Wu


Abstract
We discuss various improvements to our MEANT tuned system, previously presented at IWSLT 2013. In our 2014 system, we incorporate this year’s improved version of MEANT, improved Chinese word segmentation, Chinese named entity recognition and dedicated proper name translation, and number expression handling. This results in a significant performance jump compared to last year’s system. We also ran preliminary experiments on tuning to IMEANT, our new ITG based variant of MEANT. The performance of tuning to IMEANT is comparable to tuning on MEANT (differences are statistically insignificant). We are presently investigating if tuning on IMEANT can produce even better results, since IMEANT was actually shown to correlate with human adequacy judgment more closely than MEANT. Finally, we ran experiments applying our new architectural improvements to a contrastive system tuned to BLEU. We observed a slightly higher jump in comparison to last year, possibly due to mismatches of MEANT’s similarity models to our new entity handling.
Anthology ID:
2014.iwslt-evaluation.4
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Editors:
Marcello Federico, Sebastian Stüker, François Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
34–41
Language:
URL:
https://aclanthology.org/2014.iwslt-evaluation.4
DOI:
Bibkey:
Cite (ACL):
Meriem Beloucif, Chi-kiu Lo, and Dekai Wu. 2014. Improving MEANT based semantically tuned SMT. In Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 34–41, Lake Tahoe, California.
Cite (Informal):
Improving MEANT based semantically tuned SMT (Beloucif et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-evaluation.4.pdf