Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection

Feng Zhang, Wei Chen, Fei Ding, Tengjiao WangACL 2023 · OpenReview

Abstract

Multi-label intent detection aims to assign multiple labels to utterances, a critical task for modern task-oriented dialogue systems. As dialogue domains evolve and new intents emerge, the scarcity of annotated data necessitates multi-label few-shot intent detection (ML-FSID). Previous approaches often struggle with identical representations for utterances containing multiple labels and fail to account for intrinsic intra-class and inter-class interactions. To address these limitations, we propose the Dual Class Knowledge Propagation Network (DCKPN). Our framework introduces a label-semantic augmentation module that incorporates class name information to learn well-separated representations. Furthermore, we construct instance-level and class-level graph neural networks to propagate both label information and feature structures. Experimental results on two multi-label intent datasets demonstrate that DCKPN significantly outperforms strong baselines.

Introduction

In task-oriented dialogue systems, intent detection is the foundational step in understanding user requests. While single-label classification is well-studied, real-world interactions often involve multi-intent utterances (e.g., "What time is my meeting and where is it located?"). Detecting these intents in a few-shot setting—where only a handful of labeled examples are available—presents two major challenges:

  1. Representation Confusion: Standard models often produce a single, blended embedding for an utterance with multiple intents, making it difficult for classifiers to isolate individual components.
  2. Overlooked Relationships: Existing models frequently treat intents as independent, ignoring high-order correlations between classes (e.g., the likelihood that a request for a 'date' is accompanied by a request for a 'time').

Methodology

DCKPN addresses these hurdles through a novel architecture consisting of three primary components: Label-semantic Augmentation, a Dual-Graph Architecture, and Adaptive Intent Counting.

Label-semantic Augmentation (LA)

To resolve representation confusion, we append label names directly to the utterance (e.g., [CLS] utterance [SEP] label_name [SEP]). This process transforms a single multi-label example into multiple label-specific samples. By forcing the encoder to process the utterance in the context of a specific intent name, the model learns more distinct, intent-aware features.

Dual Class Knowledge Propagation Network

We utilize two interconnected graphs to model complex interactions:

  • Instance-level Graph: This graph connects similar utterances to smooth their features, allowing the model to effectively generalize from the limited support set to query instances.
  • Class-level Graph: This component models the relationships between the intents themselves. By leveraging the instance-level graph to generate pseudo-class representations for query samples, the model can infer label correlations even for previously unseen data.
Overview of the DCKPN architecture, illustrating the Label-semantic Augmentation and the dual-graph propagation mechanism.

Adaptive Intent Counting

Instead of relying on a fixed similarity threshold to determine intent presence, DCKPN employs a simple Multi-Layer Perceptron (MLP) to predict the exact number of intents within a given utterance. This adaptive approach is more robust to the varying complexity of user queries.

Experimental Evaluation

We evaluated DCKPN on two benchmark datasets: TourSG (tourism in Singapore) and StanfordLU (Schedule, Navigate, and Weather domains). We used Electra-small and BERT-base as the underlying text encoders.

Key Results

DCKPN achieved a new state-of-the-art across both datasets, particularly in the challenging 1-shot setting:

  • StanfordLU (1-shot): DCKPN reached an F1 score of 56.58%, a dramatic 14% absolute improvement over the previous best model, CTLR (42.51%).
  • TourSG (1-shot): DCKPN achieved 54.93% F1, outperforming CTLR's 51.07%.

Ablation studies confirmed that Label-semantic Augmentation is the most critical component, as removing it led to the most significant performance degradation. This highlights the value of using intent names as a "free" semantic signal.

t-SNE visualization of the embeddings produced by DCKPN, demonstrating the model's ability to produce well-separated clusters for different intent classes.

Conclusion

DCKPN demonstrates that incorporating label semantics and modeling dual-level interactions (instance and class) provides a powerful framework for multi-label few-shot intent detection. By treating semantics as a signal and allowing bidirectional knowledge flow between graphs, the model achieves superior generalization. Future work will explore more sophisticated prompt engineering and the integration of intent detection with slot filling for holistic dialogue understanding.

Summary updated

Abstract

Multi-label intent detection aims to assign multiple labels to utterances and attracts increasing attention as a practical task in task-oriented dialogue systems. As dialogue domains change rapidly and new intents emerge fast, the lack of annotated data motivates multi-label few-shot intent detection. However, previous studies are confused by the identical representation of the utterance with multiple labels and overlook the intrinsic intra-class and inter-class interactions. To address these two limitations, we propose a novel dual class knowledge propagation network in this paper. In order to learn well-separated representations for utterances with multiple intents, we first introduce a label-semantic augmentation module incorporating class name information. For better consideration of the inherent intra-class and inter-class relations, an instance-level and a class-level graph neural network are constructed, which not only propagate label information but also propagate feature structure. And we use a simple yet effective method to predict the intent count of each utterance. Extensive experimental results on two multi-label intent datasets have demonstrated that our proposed method outperforms strong baselines by a large margin.
BibTeX
@inproceedings{zhang2023dual,
  author = {Feng Zhang and Wei Chen and Fei Ding and Tengjiao Wang},
  title = {{Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection}},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  year = {2023},
  url = {https://openreview.net/forum?id=xjHMpsGvMV},
}
Figure