HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

LISN @ WMT 2021

Jitao Xu 1 Sadaf Abdul Rauf 1 Minh Quang Pham 1, 2 François Yvon 1
1 TLP - Traitement du Langage Parlé
LISN - Laboratoire Interdisciplinaire des Sciences du Numérique, STL - Sciences et Technologies des Langues
Abstract : This paper describes LISN's submissions to two shared tasks at WMT'21. For the biomedical translation task, we have developed resource-heavy systems for the English-French language pair, using both out-ofdomain and in-domain corpora. The target genre for this task (scientific abstracts) corresponds to texts that often have a standardized structure. Our systems attempt to take this structure into account using a hierarchical system of sentence-level tags. Translation systems were also prepared for the News task for the French-German language pair. The challenge was to perform unsupervised adaptation to the target domain (financial news). For this, we explored the potential of retrieval-based strategies, where sentences that are similar to test instances are used to prime the decoder.
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03430610
Contributor : François Yvon Connect in order to contact the contributor
Submitted on : Friday, November 19, 2021 - 6:01:39 PM
Last modification on : Monday, December 13, 2021 - 9:17:34 AM
Long-term archiving on: : Sunday, February 20, 2022 - 6:09:36 PM

File

2021.wmt-1.22.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-03430610, version 1

Collections

Citation

Jitao Xu, Sadaf Abdul Rauf, Minh Quang Pham, François Yvon. LISN @ WMT 2021. 6th Conference on Statistical Machine Translation, Association for Computational Linguistics, Nov 2021, Punta Cuna, Dominica. ⟨hal-03430610⟩

Share

Metrics

Record views

39

Files downloads

31