Difference between revisions of "Language Translation"

From
Jump to: navigation, search
m
m
Line 12: Line 12:
 
** [[Animal Language]]
 
** [[Animal Language]]
 
* [[End-to-End Speech]]
 
* [[End-to-End Speech]]
 +
* [[Hugging Face]]
 
* [http://source.wustl.edu/2019/05/machine-learning-reduces-language-barriers-in-global-trade-research-shows/ Machine learning reduces language barriers in global trade, research shows Using eBay data, scientists find 10.9% trade increase due to AI translation | Kurt Greenbaum - Washington University in St. Louis]
 
* [http://source.wustl.edu/2019/05/machine-learning-reduces-language-barriers-in-global-trade-research-shows/ Machine learning reduces language barriers in global trade, research shows Using eBay data, scientists find 10.9% trade increase due to AI translation | Kurt Greenbaum - Washington University in St. Louis]
 
* [http://code.fb.com/ai-research/unsupervised-machine-translation-a-novel-approach-to-provide-fast-accurate-translations-for-more-languages/ Unsupervised machine translation: A novel approach to provide fast, accurate translations for more languages | M.A. Ranzato, G. Lample, & M. Ott]
 
* [http://code.fb.com/ai-research/unsupervised-machine-translation-a-novel-approach-to-provide-fast-accurate-translations-for-more-languages/ Unsupervised machine translation: A novel approach to provide fast, accurate translations for more languages | M.A. Ranzato, G. Lample, & M. Ott]
Line 28: Line 29:
 
<youtube>nRBnh4qbPHI</youtube>
 
<youtube>nRBnh4qbPHI</youtube>
  
== HuggingFace NLP Library - Open Parallel Corpus (OPUS) ==
 
* [http://venturebeat.com/2020/05/16/hugging-face-dives-into-machine-translation-with-release-of-1000-models/ [[Hugging Face]] dives into machine translation with release of 1,000 models | Khari Johnson - VentureBeat]
 
* [http://towardsdatascience.com/build-your-own-machine-translation-service-with-transformers-d0709df0791b Build Your Own Machine Translation Service with Transformers Using the latest Helsinki NLP models available in the Transformers library to create a standardized machine translation service | Kyle Gallatin - Towards Data Science]
 
[[Hugging Face]]
 
  
OPUS is a growing collection of translated texts from the web. In the OPUS project we try to convert and align free online data, to add linguistic annotation, and to provide the community with a publicly available parallel corpus. OPUS is a project undertaken by the University of Helsinki and global partners to gather and open-source a wide variety of language data sets.
 
OPUS is based on open source products and the corpus is also delivered as an open content package. We used several tools to compile the current collection. All pre-processing is done automatically. No manual corrections have been carried out. The OPUS collection is growing!
 
[http://opus.nlpl.eu/ ... OPUS the open parallel corpus]
 
 
<youtube>G3pOvrKkFuk</youtube>
 
<youtube>G5lmya6eKtc</youtube>
 
  
  

Revision as of 07:46, 4 February 2023