Monash University’s submissions to the WNGT 2019 document translation task

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

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.

Original languageEnglish
Title of host publicationEMNLP-IJCNLP 2019
Subtitle of host publicationNeural Generation and Translation, Proceedings of the Third Workshop
EditorsAlexandra Birch, Andrew Finch, Hiroaki Hayashi, Ioannis Konstas, Thang Luong, Graham Neubig, Yusuke Oda, Katsuhito Sudoh
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Pages256-261
Number of pages6
ISBN (Electronic)781950737833
DOIs
Publication statusPublished - 2019
EventWorkshop on Neural Generation and Translation 2019 - Hong Kong, China
Duration: 4 Nov 20194 Nov 2019
Conference number: 3rd

Conference

ConferenceWorkshop on Neural Generation and Translation 2019
Abbreviated titleEMNLP-IJCNLP 2019
Country/TerritoryChina
CityHong Kong
Period4/11/194/11/19

Cite this