用用户意图增强对话信息，提升少样本对话状态跟踪效果
Intent-driven In-context Learning for Few-shot Dialogue State Tracking
- 根据用户意图增强对话上下文信息
- 在多轮对话数据上实现领先性能，少样本下准确率超基线
- 适合需要低资源对话系统研发的场景
对话状态跟踪（DST）在任务导向型对话系统中至关重要。然而，用户输入常含隐含信息，且数据包含大量与当前轮次无关的噪声，导致构建高质量数据集成本高昂。为此，我们提出意图驱动的上下文学习方法（IDIC-DST），通过提取用户意图，设计意图驱动的信息增强模块来补充对话内容；同时，在示例检索模块中屏蔽噪声并重构用户输入以获取相似样例；最后利用预训练大模型基于增强后的对话信息与检索样例更新状态。实验表明，IDIC-DST在多轮对话数据集MultiWOZ 2.1和MultiWOZ 2.4的少样本设置下均达到当前最优性能。
原文摘要 · Abstract (English)
Dialogue state tracking (DST) plays an essential role in task-oriented dialogue systems. However, user's input may contain implicit information, posing significant challenges for DST tasks. Additionally, DST data includes complex information, which not only contains a large amount of noise unrelated to the current turn, but also makes constructing DST datasets expensive. To address these challenges, we introduce Intent-driven In-context Learning for Few-shot DST (IDIC-DST). By extracting user's intent, we propose an Intent-driven Dialogue Information Augmentation module to augment the dialogue information, which can track dialogue states more effectively. Moreover, we mask noisy information from DST data and rewrite user's input in the Intent-driven Examples Retrieval module, where we retrieve similar examples. We then utilize a pre-trained large language model to update the dialogue state using the augmented dialogue information and examples. Experimental results demonstrate that IDIC-DST achieves state-of-the-art performance in few-shot settings on MultiWOZ 2.1 and MultiWOZ 2.4 datasets.
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。