Pseudo Siamese Network for Few-shot Intent Generation
This addresses the scarcity of annotations for intent detection in conversational AI, but it is incremental as it builds on existing few-shot and generative methods.
The paper tackles the problem of few-shot intent detection by proposing a Pseudo Siamese Network (PSN) to generate labeled data, achieving state-of-the-art performance on two real-world datasets.
Few-shot intent detection is a challenging task due to the scare annotation problem. In this paper, we propose a Pseudo Siamese Network (PSN) to generate labeled data for few-shot intents and alleviate this problem. PSN consists of two identical subnetworks with the same structure but different weights: an action network and an object network. Each subnetwork is a transformer-based variational autoencoder that tries to model the latent distribution of different components in the sentence. The action network is learned to understand action tokens and the object network focuses on object-related expressions. It provides an interpretable framework for generating an utterance with an action and an object existing in a given intent. Experiments on two real-world datasets show that PSN achieves state-of-the-art performance for the generalized few shot intent detection task.