融合新旧知识，让模型自动发现未知意图并提升泛化能力
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
- 用原型提示机制迁移已有知识，实现跨域知识复用
- 通过分层一致性约束，在无标注数据中发现新意图，准确率显著提升
- 适合需要持续学习新用户意图的智能客服、对话系统场景
意图识别旨在从自然语言输入中识别用户意图，现有监督方法严重依赖标注的域内（IND）数据，难以处理域外（OOD）意图，限制了实际应用。广义意图发现（GID）通过利用未标注的域外数据，在无需额外标注的情况下发现新意图。然而，现有方法仅关注无监督聚类，忽视领域适应。为此，本文提出一种一致性驱动的原型提示框架，从新旧知识融合视角解决GID问题，包含基于原型提示的知识迁移机制，以及用于从目标域学习新知识的分层一致性约束。大量实验表明，该方法显著优于所有基线，达到当前最优性能，充分验证了其有效性和泛化能力。代码已开源：https://github.com/smileix/cpp。
原文摘要 · Abstract (English)
Intent detection aims to identify user intents from natural language inputs, where supervised methods rely heavily on labeled in-domain (IND) data and struggle with out-of-domain (OOD) intents, limiting their practical applicability. Generalized Intent Discovery (GID) addresses this by leveraging unlabeled OOD data to discover new intents without additional annotation. However, existing methods focus solely on clustering unsupervised data while neglecting domain adaptation. Therefore, we propose a consistency-driven prototype-prompting framework for GID from the perspective of integrating old and new knowledge, which includes a prototype-prompting framework for transferring old knowledge from external sources, and a hierarchical consistency constraint for learning new knowledge from target domains. We conducted extensive experiments and the results show that our method significantly outperforms all baseline methods, achieving state-of-the-art results, which strongly demonstrates the effectiveness and generalization of our methods. Our source code is publicly available at https://github.com/smileix/cpp.
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。