Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with generated pseudo samples. However, most existing generative replay methods use only a single task-specific token to control their models. This scheme is usually not strong enough to constrain the generative model due to insufficient information involved. In this paper, we propose a novel method, prompt conditioned VAE for lifelong learning (PCLL), to enhance generative replay by incorporating tasks' statistics. PCLL captures task-specific distributions with a conditional variational autoencoder, conditioned on natural language prompts to guide the pseudo-sample generation. Moreover, it leverages a distillation process to further consolidate past knowledge by alleviating the noise in pseudo samples. Experiments on natural language understanding tasks of ToD systems demonstrate that PCLL significantly outperforms competitive baselines in building LL models.
Code (1)
Tasks
Lifelong learningNatural Language UnderstandingSimilar Papers 제목 키워드 기반
Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent Detection
Identifying all possible user intents for a dialog system at design time is challenging even for skilled domain experts. For practical applications, novel intents may have to be inferred incrementally on the fly. This ty…
Continual LearningContrastive LearningIntent DetectionRelation ExtractionLifelong GAN: Continual Learning for Conditional Image Generation
Lifelong learning is challenging for deep neural networks due to their susceptibility to catastrophic forgetting. Catastrophic forgetting occurs when a trained network is not able to maintain its ability to accomplish pr…
Conditional Image GenerationContinual LearningImage GenerationKnowledge Distillation+1Learning latent representations across multiple data domains using Lifelong VAEGAN
The problem of catastrophic forgetting occurs in deep learning models trained on multiple databases in a sequential manner. Recently, generative replay mechanisms (GRM), have been proposed to reproduce previously learned…
Lifelong learningRepresentation LearningLifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
We introduce the eigentask framework for lifelong learning. An eigentask is a pairing of a skill that solves a set of related tasks, paired with a generative model that can sample from the skill's input space. The framew…
Continual LearningLifelong learningTransfer LearningLifelong Learning using Eigentasks: Task Separation, Skill Acquisition and Selective Transfer
We introduce the eigentask framework for lifelong learning. An eigentask is a pairing of a skill that solves a set of related tasks with a generative model that can sample from the skill's input space. The model extends …
Continual LearningLifelong learningStarcraftTransfer Learning