Domain Adaptation in Neural Machine Translation using a Qualia-Enriched FrameNet
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A2CAQ7NWX" target="_blank" >RIV/00216208:11320/22:2CAQ7NWX - isvavai.cz</a>
Result on the web
<a href="http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.1.pdf" target="_blank" >http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.1.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Domain Adaptation in Neural Machine Translation using a Qualia-Enriched FrameNet
Original language description
In this paper we present Scylla, a methodology for domain adaptation of Neural Machine Translation (NMT) systems that make use of a multilingual FrameNet enriched with qualia relations as an external knowledge base. Domain adaptation techniques used in NMT usually require fine-tuning and in-domain training data, which may pose difficulties for those working with lesser-resourced languages and may also lead to performance decay of the NMT system for out-of-domain sentences. Scylla does not require fine-tuning of the NMT model, avoiding the risk of model over-fitting and consequent decrease in performance for out-of-domain translations. Two versions of Scylla are presented: one using the source sentence as input, and another one using the target sentence. We evaluate Scylla in comparison to a state-of-the-art commercial NMT system in an experiment in which 50 sentences from the Sports domain are translated from Brazilian Portuguese to English. The two versions of Scylla significantly outperform the baseline commercial system in HTER.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022)
ISBN
979-10-95546-72-6
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
1-12
Publisher name
European Language Resources Association (ELRA)
Place of publication
—
Event location
Marseille, France
Event date
Jan 1, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—