monologg/JointBERT
A PyTorch implementation of BERT for simultaneous intent classification and slot filling in conversational NLP.
Not currently ranked — collecting fresh signals.
star history
JointBERT implements the BERT-based model from the 2019 paper for Joint Intent Classification and Slot Filling. The model processes text through a BERT encoder to simultaneously predict the user intent and fill slot labels (e.g., identifying entities like locations or dates) in a single forward pass, optimizing a combined loss function. It supports optional CRF layers for enhanced sequence labeling and was evaluated on the ATIS and Snips benchmark datasets.
Frequently asked
- What is monologg/JointBERT?
- A PyTorch implementation of BERT for simultaneous intent classification and slot filling in conversational NLP.
- Is JointBERT open source?
- Yes — monologg/JointBERT is open source, released under the Apache-2.0 license.
- What language is JointBERT written in?
- monologg/JointBERT is primarily written in Python.
- How popular is JointBERT?
- monologg/JointBERT has 747 stars on GitHub.
- Where can I find JointBERT?
- monologg/JointBERT is on GitHub at https://github.com/monologg/JointBERT.