Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
arXiv:1609.01462
Abstract
Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection, slot filling, and language modeling. The neural network model keeps updating the intent estimation as word in the transcribed utterance arrives and uses it as contextual features in the joint model. Evaluation of the language model and online SLU model is made on the ATIS benchmarking data set. On language modeling task, our joint model achieves 11.8% relative reduction on perplexity comparing to the independent training language model. On SLU tasks, our joint model outperforms the independent task training model by 22.3% on intent detection error rate, with slight degradation on slot filling F1 score. The joint model also shows advantageous performance in the realistic ASR settings with noisy speech input.
arXiv commentAccepted at SIGDIAL 2016
References in corpus (4)
Cited by in corpus (10)
- Spoken Language Intent Detection using Confusion2Vec
- Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
- A Survey on Spoken Language Understanding: Recent Advances and New Frontiers
- Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
- Conversational Intent Understanding for Passengers in Autonomous Vehicles
- OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding
- Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
- Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant
- Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks
- CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots