Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges

2025-12-11

AI Summary

Multi-intent spoken language understanding (SLU) requires simultaneous intent detection and slot filling, yet existing literature lacks a systematic survey. This paper presents the first unified taxonomy, classifying over 60 works along two orthogonal dimensions: decoding paradigms (e.g., autoregressive, parallel, structured) and modeling pathways (e.g., sequence labeling, joint modeling, graph neural networks, and large language model adaptation), while integrating techniques such as multi-task learning, label augmentation, and structured decoding. Through critical analysis, we identify key bottlenecks—including limited generalizability under compositional intent distributions, dataset biases toward frequent intent combinations, and evaluation inconsistencies due to ambiguous metrics and underspecified test sets. We propose promising research directions, notably scalable decoding architectures and explicit intent relation modeling. Our synthesis bridges theoretical advancement and practical deployment, offering a foundational framework for next-generation multi-intent dialogue systems.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Multi-intent spoken language understanding (SLU) involves two tasks: multiple intent detection and slot filling, which jointly handle utterances containing more than one intent. Owing to this characteristic, which closely reflects real-world applications, the task has attracted increasing research attention, and substantial progress has been achieved. However, there remains a lack of a comprehensive and systematic review of existing studies on multi-intent SLU. To this end, this paper presents a survey of recent advances in multi-intent SLU. We provide an in-depth overview of previous research from two perspectives: decoding paradigms and modeling approaches. On this basis, we further compare the performance of representative models and analyze their strengths and limitations. Finally, we discuss the current challenges and outline promising directions for future research. We hope this survey will offer valuable insights and serve as a useful reference for advancing research in multi-intent SLU.

Problem

• Summarizes recent advances in multi-intent spoken language understanding.
• Compares performance of models for multiple intent detection and slot filling.
• Outlines challenges and future directions in multi-intent SLU research.

Innovation

• Survey reviews multi-intent SLU decoding paradigms
• Compares performance of representative modeling approaches
• Analyzes strengths, limitations, and future research directions