DE eng

Search in the Catalogues and Directories

Hits 1 – 9 of 9

1
Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages ...
Abstract: For most language combinations, parallel data is either scarce or simply unavailable. To address this, unsupervised machine translation (UMT) exploits large amounts of monolingual data by using synthetic data generation techniques such as back-translation and noising, while self-supervised NMT (SSNMT) identifies parallel sentences in smaller comparable data and trains on them. To date, the inclusion of UMT data generation techniques in SSNMT has not been investigated. We show that including UMT techniques into SSNMT significantly outperforms SSNMT and UMT on all tested language pairs, with improvements of up to +4.3 BLEU, +50.8 BLEU, +51.5 over SSNMT, statistical UMT and hybrid UMT, respectively, on Afrikaans to English. We further show that the combination of multilingual denoising autoencoding, SSNMT with backtranslation and bilingual finetuning enables us to learn machine translation even for distant language pairs for which only small amounts of monolingual data are available, e.g. yielding BLEU scores ... : 11 pages, 8 figures, accepted at MT-Summit 2021 (Research Track) ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.2107.08772
https://arxiv.org/abs/2107.08772
BASE
Hide details
2
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification ...
BASE
Show details
3
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe ...
BASE
Show details
4
Linguistically inspired morphological inflection with a sequence to sequence model ...
BASE
Show details
5
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers ...
BASE
Show details
6
INFODENS: An Open-source Framework for Learning Text Representations ...
BASE
Show details
7
Massively Multilingual Neural Grapheme-to-Phoneme Conversion ...
BASE
Show details
8
An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification ...
BASE
Show details
9
Predicting the Law Area and Decisions of French Supreme Court Cases ...
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
9
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern