A Joint and Domain-Adaptive Approach to Spoken Language Understanding
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 25 Jul 2021.
Builds on
26 of 36 references.
References · 26
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2017Decoupled Weight Decay Regularizationcited by 1,722
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
- 2015Pointer Networkscited by 882
- 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
- 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
- 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
- 2018Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialogcited by 124
- 2019A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understandingcited by 106
14 more
- 2019A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Fillingcited by 85
- 2019Deep Unknown Intent Detection with Margin Losscited by 66
- 2018Zero-shot User Intent Detection via Capsule Neural Networkscited by 54
- 2020Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inferencecited by 47
- 2020SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Fillingcited by 42
- 2017Towards Zero-Shot Frame Semantic Parsing for Domain Scalingcited by 40
- 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
- 2020Coach: A Coarse-to-Fine Approach for Cross-domain Slot Fillingcited by 38
- 2019CM-Net: A Novel Collaborative Memory Network for Spoken Language Understandingcited by 34
- 2018OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understandingcited by 13
- 2016Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understandingcited by 9
- 2017Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understandingcited by 6
- 2020Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterizationcited by 4
- 2019Locale-agnostic Universal Domain Classification Model in Spoken Language Understandingcited by 1
Built on by
Citing papers per year: 2022: 1.
1 paper.