DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 59

1
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer ...
BASE
Show details
2
Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language ...
BASE
Show details
3
Generic resources are what you need: Style transfer tasks without task-specific parallel training data ...
Abstract: Style transfer aims to rewrite a source text in a different target style while preserving its content. We propose a novel approach to this task that leverages generic resources, and without using any task-specific parallel (source-target) data outperforms existing unsupervised approaches on the two most popular style transfer tasks: formality transfer and polarity swap. In practice, we adopt a multi-step procedure which builds on a generic pre-trained sequence-to-sequence model (BART). First, we strengthen the model's ability to rewrite by further pre-training BART on both an existing collection of generic paraphrases, as well as on synthetic pairs created using a general-purpose lexical resource. Second, through an iterative back-translation approach, we train two models, each in a transfer direction, so that they can provide each other with synthetically generated pairs, dynamically in the training process. Lastly, we let our best reresulting model generate static synthetic pairs to be used in a supervised ... : Accepted to EMNLP2021 (main conference) ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/2109.04543
https://dx.doi.org/10.48550/arxiv.2109.04543
BASE
Hide details
4
A set of recommendations for assessing human-machine parity in language translation
In: Läubli, Samuel orcid:0000-0001-5362-4106 , Castilho, Sheila orcid:0000-0002-8416-6555 , Neubig, Graham, Sennrich, Rico orcid:0000-0002-1438-4741 , Shen, Qinlan and Toral, Antonio orcid:0000-0003-2357-2960 (2020) A set of recommendations for assessing human-machine parity in language translation. Journal of Artificial Intelligence Research, 67 . pp. 653-672. ISSN 1076-9757 (2020)
BASE
Show details
5
Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT ...
BASE
Show details
6
A Set of Recommendations for Assessing Human-Machine Parity in Language Translation ...
BASE
Show details
7
Editors’ foreword to the special issue on human factors in neural machine translation [<Journal>]
Castilho, Sheila [Verfasser]; Gaspari, Federico [Verfasser]; Moorkens, Joss [Verfasser].
DNB Subject Category Language
Show details
8
Post-editing effort of a novel with statistical and neural machine translation
In: Toral, Antonio, Wieling, Martijn and Way, Andy orcid:0000-0001-5736-5930 (2018) Post-editing effort of a novel with statistical and neural machine translation. Frontiers in Digital Humanities, 5 (9). pp. 1-11. ISSN 2297-2668 (2018)
BASE
Show details
9
What level of quality can neural machine translation attain on literary text?
In: Toral, Antonio orcid:0000-0003-2357-2960 and Way, Andy orcid:0000-0001-5736-5930 (2018) What level of quality can neural machine translation attain on literary text? In: Moorkens, Joss orcid:0000-0003-4864-5986 , Castilho, Sheila orcid:0000-0002-8416-6555 , Gaspari, Federico orcid:0000-0003-3808-8418 and Doherty, S, (eds.) Translation Quality Assessment: From Principles to Practice. Machine Translation: Technologies and Applications book series (MATRA), 1 . Springer, Berlin/Heidelberg, 263 -287. ISBN 978-3-319-91240-0 (2018)
BASE
Show details
10
Post-editing effort of a novel with statistical and neural machine translation
In: Toral, Antonio orcid:0000-0003-2357-2960 , Wieling, Martijn orcid:0000-0003-0434-1526 and Way, Andy orcid:0000-0001-5736-5930 (2018) Post-editing effort of a novel with statistical and neural machine translation. Frontiers in Digital Humanities, 5 . ISSN 2297-2668 (2018)
BASE
Show details
11
Attaining the unattainable? Reassessing claims of human parity in neural machine translation
In: Toral, Antonio orcid:0000-0003-2357-2960 , Castilho, Sheila orcid:0000-0002-8416-6555 , Hu, Ke and Way, Andy orcid:0000-0001-5736-5930 (2018) Attaining the unattainable? Reassessing claims of human parity in neural machine translation. In: Third Conference on Machine Translation (WMT), 31 Oct- 1 Nov 2018, Brussels, Belgium. ISBN 978-1-948087-81-0 (2018)
BASE
Show details
12
Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian ...
BASE
Show details
13
Quantitative Fine-grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian
In: Articles (2018)
BASE
Show details
14
Fine-grained human evaluation of neural versus phrase-based machine translation ...
BASE
Show details
15
A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions ...
BASE
Show details
16
Fine-Grained Human Evaluation of Neural Versus Phrase-Based Machine Translation
In: Prague Bulletin of Mathematical Linguistics , Vol 108, Iss 1, Pp 121-132 (2017) (2017)
BASE
Show details
17
CloudLM: a cloud-based language model for machine translation
In: Ferrández-Tordera, Jorge, Ortiz-Rojas, Sergio and Toral, Antonio orcid:0000-0003-2357-2960 (2016) CloudLM: a cloud-based language model for machine translation. Prague Bulletin of Mathematical Linguistics (105). pp. 51-61. ISSN 1804-0462 (2016)
BASE
Show details
18
Serbian-English parallel corpus srenWaC 1.0
Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016
BASE
Show details
19
Finnish web corpus fiWaC 1.0
Ljubešić, Nikola; Pirinen, Tommi; Toral, Antonio. - : Jožef Stefan Institute, 2016
BASE
Show details
20
Finnish-English parallel corpus fienWaC 1.0
Ljubešić, Nikola; Esplà-Gomis, Miquel; Ortiz Rojas, Sergio. - : Jožef Stefan Institute, 2016
BASE
Show details

Page: 1 2 3

Catalogues
0
0
2
0
2
0
0
Bibliographies
1
0
0
0
0
0
1
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
54
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern