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 ...
|
|
|
|
BASE
|
|
Show 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
|
|
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)
|
|
Abstract:
We conduct the first experiment in the literature in which a novel is translated automatically and then post-edited by professional literary translators. Our case study is Warbreaker, a popular fantasy novel originally written in English, which we translate into Catalan. We translated one chapter of the novel (over 3,700 words, 330 sentences) with two data-driven approaches to Machine Translation (MT): phrase-based statistical MT (PBMT) and neural MT (NMT). Both systems are tailored to novels; they are trained on over 100 million words of fiction. In the post-editing experiment, six professional translators with previous experience in literary translation translate subsets of this chapter under three alternating conditions: from scratch (the norm in the novel translation industry), post-editing PBMT, and post-editing NMT. We record all the keystrokes, the time taken to translate each sentence, as well as the number of pauses and their duration. Based on these measurements, and using mixed-effects models, we study post-editing effort across its three commonly studied dimensions: temporal, technical and cognitive. We observe that both MT approaches result in increases in translation productivity: PBMT by 18%, and NMT by 36%. Post-editing also leads to reductions in the number of keystrokes: by 9% with PBMT, and by 23% with NMT. Finally, regarding cognitive effort, post-editing results in fewer (29 and 42% less with PBMT and NMT, respectively) but longer pauses (14 and 25%).
|
|
Keyword:
foreign fiction; foreign literature; literary translation; Machine translating; neural machine translation; post-editing; statistical machine translation
|
|
URL: http://doras.dcu.ie/23364/
|
|
BASE
|
|
Hide 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
|
|
|
|