通过伪标签增强原型对比学习，统一解决新意图发现中的跨域迁移问题。
Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery
- 迭代使用伪标签挖掘正负样本，连接表征与聚类过程
- 融合有监督信号与伪标签，提升跨域知识迁移能力
- 在两种设置下均有效，适用于开放意图与跨域场景
新意图发现是任务导向对话系统的关键能力。现有方法通常通过预训练和聚类阶段将领域内（IND）先验知识迁移到领域外（OOD）数据，但多采用流水线方式，导致表征与聚类间存在鸿沟；或使用典型对比聚类，忽视了全量数据潜在的监督信号。此外，多数方法分别处理开放意图发现或跨域设置。为此，我们提出一种伪标签增强的原型对比学习（PLPCL）模型，用于统一的新意图发现。该模型迭代利用伪标签探索对比学习中的正负样本，弥合表征与聚类间的差距。为实现更好知识迁移，设计了一种融合IND与OOD样本中监督信号与伪标签的原型学习方法。实验在三个基准数据集及两种任务设置下验证了该方法的有效性。
原文摘要 · Abstract (English)
New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either handle the two processes in a pipeline manner, which exhibits a gap between intent representation and clustering process or use typical contrastive clustering that overlooks the potential supervised signals from the whole data. Besides, they often individually deal with open intent discovery or OOD settings. To this end, we propose a Pseudo-Label enhanced Prototypical Contrastive Learning (PLPCL) model for uniformed intent discovery. We iteratively utilize pseudo-labels to explore potential positive/negative samples for contrastive learning and bridge the gap between representation and clustering. To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples. In addition, our method has been proven effective in two different settings of discovering new intents. Experiments on three benchmark datasets and two task settings demonstrate the effectiveness of our approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。