USE Embedding

The USE Embedding snippet is a model built around the Universal sentence encoder block.
The snippet can be used to quickly deploy a text processing model for semantic similarity tasks.

The snippet works with the 16 languages supported by the Universal sentence encoder block.

The USE Embedding snippet

The USE Embedding snippet includes:

How to deploy the USE Embedding snippet

Note
Disclaimer
Please note that datasets, machine-learning models, weights, topologies, research papers and other content, including open source software, (collectively referred to as “Content”) provided and/or suggested by Peltarion for use in the Platform and otherwise, may be subject to separate third party terms of use or license terms. You are solely responsible for complying with the applicable terms. Peltarion makes no representations or warranties about Content. You expressly relieve us from any and all liability, loss or risk arising (directly or indirectly) from Your use of any third party content.

The weights provided are pre-trained specifically for semantic text similarity. This means that in most cases the output of the Universal sentence encoder block can be used directly, without further training.

To avoid training, simply check that all the blocks in your model have un-selected the Trainable parameter.
When that is the case, clicking the Run button will only run a validation pass, and your model will be ready for deployment.

Languages supported

The USE Embedding snippet is based on the Universal sentence encoder block , which supports these 16 languages:

Arabic

French

Korean

Spanish

Chinese-simplified

German

Dutch

Thai

Chinese-traditional

Italian

Polish

Turkish

English

Japanese

Portuguese

Russian

Available weights

The Universal sentence encoder block uses the universal-sentence-encoder-multilingual model with weights released by Google.

The weights are pretrained on SNLI.

Terms

When using pretrained snippets, additional terms apply: universal sentence encoder with weights licence.

References

Was this page helpful?
YesNo