linkedin/detext
LinkedIn's DeText is an open-source deep learning framework for NLP ranking, classification, and language generation tasks built on TensorFlow.
Not currently ranked — collecting fresh signals.
star history
DeText provides end-to-end neural text understanding using configurable CNN, BERT, and LSTM encoders with interaction modeling for semantic matching. It supports search ranking, multi-class classification, and query understanding through deep neural networks that automatically extract features from text data.
Frequently asked
- What is linkedin/detext?
- LinkedIn's DeText is an open-source deep learning framework for NLP ranking, classification, and language generation tasks built on TensorFlow.
- Is detext open source?
- Yes — linkedin/detext is open source, released under the BSD-2-Clause license.
- What language is detext written in?
- linkedin/detext is primarily written in Python.
- How popular is detext?
- linkedin/detext has 1.3k stars on GitHub.
- Where can I find detext?
- linkedin/detext is on GitHub at https://github.com/linkedin/detext.