A Survey on Spoken Language Understanding: Recent Advances and New Frontiers
arXiv:2103.03095
Abstract
Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system. With the burst of deep neural networks and the evolution of pre-trained language models, the research of SLU has obtained significant breakthroughs. However, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. In this paper, we survey recent advances and new frontiers in SLU. Specifically, we give a thorough review of this research field, covering different aspects including (1) new taxonomy: we provide a new perspective for SLU filed, including single model vs. joint model, implicit joint modeling vs. explicit joint modeling in joint model, non pre-trained paradigm vs. pre-trained paradigm;(2) new frontiers: some emerging areas in complex SLU as well as the corresponding challenges; (3) abundant open-source resources: to help the community, we have collected, organized the related papers, baseline projects and leaderboard on a public website where SLU researchers could directly access to the recent progress. We hope that this survey can shed a light on future research in SLU field.
arXiv commentAccepted at IJCAI2021. Resources in \url{https://github.com/yizhen20133868/Awesome-SLU-Survey}
References in corpus (6)
- Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
- Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Model
- Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
- Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
- Dialogue State Induction Using Neural Latent Variable Models
- Sequential Dialogue Context Modeling for Spoken Language Understanding