BERT for Joint Intent Classification and Slot Filling

Code

• github.com/alibaba-damo-academy/spokennlp
  tf★ 125
• github.com/MahmoudWahdan/dialog-nlu
  tf★ 100
• github.com/VinAIResearch/JointIDSF
  pytorch★ 88
• github.com/dsindex/iclassifier
  pytorch★ 44
• github.com/sxjscience/GluonNLP-Slot-Filling
  mxnet★ 0
• github.com/zhoucz97/JointBERT-paddle
  paddle★ 0
• github.com/mangushev/intent_slot
  tf★ 0
• github.com/Polly42Rose/SiriusIntentPredictionSlotFilling
  pytorch★ 0
• github.com/sonos/svc-demographic-bias-assessment
  none★ 0
• github.com/yinghao1019/Joint_learn
  pytorch★ 0

Abstract

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort on exploring BERT for natural language understanding. In this work, we propose a joint intent classification and slot filling model based on BERT. Experimental results demonstrate that our proposed model achieves significant improvement on intent classification accuracy, slot filling F1, and sentence-level semantic frame accuracy on several public benchmark datasets, compared to the attention-based recurrent neural network models and slot-gated models.

Tasks

Benchmark Results

Reproductions