DE eng

Search in the Catalogues and Directories

Hits 1 – 12 of 12

1
Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language ...
Abstract: This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German--Lower Sorbian (DE--DSB): a high-resource language to a low-resource one. Our system uses a transformer encoder-decoder architecture in which we make three changes to the standard training procedure. First, our training focuses on two languages at a time, contrasting with a wealth of research on multilingual systems. Second, we introduce a novel method for initializing the vocabulary of an unseen language, achieving improvements of 3.2 BLEU for DE$\rightarrow$DSB and 4.0 BLEU for DSB$\rightarrow$DE. Lastly, we experiment with the order in which offline and online back-translation are used to train an unsupervised system, finding that using online back-translation first works better for DE$\rightarrow$DSB by 2.76 BLEU. Our submissions ranked first (tied with another team) for DSB$\rightarrow$DE and third for DE$\rightarrow$DSB. ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/2109.12012
https://dx.doi.org/10.48550/arxiv.2109.12012
BASE
Hide details
2
On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions ...
BASE
Show details
3
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters ...
BASE
Show details
4
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters ...
BASE
Show details
5
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding ...
BASE
Show details
6
On the Difficulty of Translating Free-Order Case-Marking Languages ...
BASE
Show details
7
UDapter: Language Adaptation for Truly Universal Dependency Parsing ...
BASE
Show details
8
FiSSA at SemEval-2020 Task 9: Fine-tuned For Feelings ...
BASE
Show details
9
Incorporating word embeddings in unsupervised morphological segmentation
In: 2020 ; 1 ; 21 (2020)
BASE
Show details
10
Characters or morphemes: how to represent words?
Üstün, Ahmet; Kurfalı, Murathan; Can, Burcu. - : Association for Computational Linguistics, 2018
BASE
Show details
11
A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation ...
BASE
Show details
12
Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets ...
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
12
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern