HadoopIt/rnn-nlu
A TensorFlow implementation of attention-based RNN/LSTM models for natural language understanding tasks including intent detection and slot filling.

Velocity · 7d
+0.1
★ / day
Trend
→steady
star history
This repository provides a TensorFlow implementation of attention-based recurrent neural networks for sequence classification and sequence labeling. The models target spoken language understanding, performing joint intent detection and slot filling tasks on the ATIS dataset. It supports bidirectional RNNs and attention mechanisms, with configurable multi-task training for classification and tagging objectives.