Monash University’s Submissions to the WNGT 2019 Document Translation Task

Sameen Maruf, Gholamreza Haffari


Abstract
We describe the work of Monash University for the shared task of Rotowire document translation organised by the 3rd Workshop on Neural Generation and Translation (WNGT 2019). We submitted systems for both directions of the English-German language pair. Our main focus is on employing an established document-level neural machine translation model for this task. We achieve a BLEU score of 39.83 (41.46 BLEU per WNGT evaluation) for En-De and 45.06 (47.39 BLEU per WNGT evaluation) for De-En translation directions on the Rotowire test set. All experiments conducted in the process are also described.
Anthology ID:
D19-5628
Volume:
Proceedings of the 3rd Workshop on Neural Generation and Translation
Month:
November
Year:
2019
Address:
Hong Kong
Editors:
Alexandra Birch, Andrew Finch, Hiroaki Hayashi, Ioannis Konstas, Thang Luong, Graham Neubig, Yusuke Oda, Katsuhito Sudoh
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
256–261
Language:
URL:
https://aclanthology.org/D19-5628
DOI:
10.18653/v1/D19-5628
Bibkey:
Cite (ACL):
Sameen Maruf and Gholamreza Haffari. 2019. Monash University’s Submissions to the WNGT 2019 Document Translation Task. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 256–261, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Monash University’s Submissions to the WNGT 2019 Document Translation Task (Maruf & Haffari, NGT 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5628.pdf