面向广义意图发现的伪标签消歧与表示学习解耦
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
AI总结:
本文提出解耦原型学习框架DPL,通过原型对比表示学习PCL和基于原型的标签消歧PLD协同工作,解决广义意图发现中伪标签消歧与表示学习相互耦合的问题。
摘要:
广义意图发现旨在将封闭集合的域内意图分类器扩展到包含域内和域外意图的开放世界意图集合。关键挑战在于伪标签消歧和表示学习。以往方法存在伪标签消歧与表示学习相互耦合的问题,即伪标签的可靠性依赖于表示学习,而表示学习又反过来受到伪标签的限制。本文提出了一种解耦原型学习框架(DPL),以解耦伪标签消歧和表示学习。具体而言,我们首先引入原型对比表示学习(PCL)来获得具有判别性的表示。然后采用基于原型的标签消歧方法(PLD)来获取伪标签。我们从理论上证明PCL和PLD以协同方式工作,并促进伪标签消歧。在三个基准数据集上的实验和分析表明了该方法的有效性。
英文摘要:
Generalized intent discovery aims to extend a closed-set in-domain intent classifier to an open-world intent set including in-domain and out-of-domain intents. The key challenges lie in pseudo label disambiguation and representation learning. Previous methods suffer from a coupling of pseudo label disambiguation and representation learning, that is, the reliability of pseudo labels relies on representation learning, and representation learning is restricted by pseudo labels in turn. In this paper, we propose a decoupled prototype learning framework (DPL) to decouple pseudo label disambiguation and representation learning. Specifically, we firstly introduce prototypical contrastive representation learning (PCL) to get discriminative representations. And then we adopt a prototype-based label disambiguation method (PLD) to obtain pseudo labels. We theoretically prove that PCL and PLD work in a collaborative fashion and facilitate pseudo label disambiguation. Experiments and analysis on three benchmark datasets show the effectiveness of our method.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。