WordNet VS Microsoft Translator

WordNet Reviews

Microsoft Translator Reviews

WordNet mentions (28)

• CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data

  TL;DR: The authors pretrain the model to classify images into Wordnet synsets[a] that appear in the caption, using a standard Cross Entropy loss. They keep the number of classes relatively small by removing any synsets that don't show up in captions at least 500 times in the dataset. It seems to work well. My immediate question is: Why not classify among the entire hierarchy of all Wordnet synsets? --- [a]... - Source: Hacker News / 25 days ago

• A History of CLIP Model Training Data Advances

  To operationalize this intuition, the Microsoft and UC Berkeley researchers use WordNet and Wiktionary to augment the text in image-text pairs. The concept itself is augmented for isolated concepts, such as the class labels in ImageNet, whereas for captions (such as from GCC), the least common noun phrase is augmented. Equipped with this additional structured knowledge, contrastively pretrained models exhibit... - Source: dev.to / 2 months ago

• GraphWords: Visual Dictionary and Thesaurus

  If you like this, definitely check out WordNet (https://wordnet.princeton.edu/). - Source: Hacker News / 5 months ago

• i was looking for a site where i could add characteristics of a words and then i could search for another words like that word.

  I didn't understand well what you meant, but maybe this site can help you: https://wordnet.princeton.edu/. Source: over 1 year ago

• Seeking a robust English word-list of length 4096 for encoding

  What I'd do is work with a huge database like WordNet and then try to "extrapolate" BIP39 to 4096 words by creating queries against WordNet to obtain words meeting the constraints you'd like to keep. Source: over 1 year ago

Microsoft Translator mentions (8)

• How can I get subtitles or some kind of translation into Spanish while I am teaching in English?

  Do you have access to Microsoft products? They have an appthat students can add to a device that will translate your spoken words into text (you have to have the app or website open as well). There are several other Microsoft translation tools that would also work in different ways, which you may be able to use without a Microsoft license. Google’s translation tools are not as well integrated. Source: over 1 year ago

• Translation software

  Translator.microsoft.com works fine in a web browser - and all I have gotten is positive feedback from my colleagues in UA about the quality/accuracy of the translations. Source: over 1 year ago

• What invention would you want to see in your lifetime?

  Iirc Microsoft, Apple, and Google are working on this with the help of AI. We are playing around with the Microsoft Neural Machine Translator at work to assist with translation for non-English speaking patients. https://translator.microsoft.com. Source: over 1 year ago

• UNDERSTANDING THE CONCEPT OF MACHINE TRANSLATION

  It is very interesting to understand how Machine Translation engines work such as Masakhane translate, Google translate, Amazon, Microsoft Translator, etc. - Source: dev.to / about 2 years ago

• Germans hosting refugees from Ukraine are rushing to learn their language — with some classes already fully booked.

  For anyone who does not know the language and is looking for an effective way to bridge the language gap: I have been using https://translator.microsoft.com/ and it has been very useful. Source: about 2 years ago