A Joint and Domain-Adaptive Approach to Spoken Language Understanding
arXiv:2107.11768
Abstract
Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other focuses on the domain-adaptation ability of one of the subtasks. In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU. We formulate SLU as a constrained generation task and utilize a dynamic vocabulary based on domain-specific ontology. We conduct experiments on the ASMixed and MTOD datasets and achieve competitive performance with previous state-of-the-art joint models. Besides, results show that our joint model can be effectively adapted to a new domain.
References in corpus (8)
- Sequence to Sequence Learning with Neural Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
- Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
- Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
- Deep Unknown Intent Detection with Margin Loss
- SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling