用大模型自动生成对话系统本体，无需人工标注。
Text-to-SQL Task-oriented Dialogue Ontology Construction
- 利用大模型的SQL能力+模块化对话系统概念，自动构建本体
- 在对话状态追踪任务中表现优于迁移学习方法
- 可扩展至维基百科和arXiv数据集，适合需要可解释性的对话系统
大语言模型虽广泛用作通用知识源，但依赖参数化知识，影响可解释性与可信度。在任务导向对话（TOD）系统中，这种分离是明确的：通过外部数据库与显式本体确保可解释性与可控性。然而，构建本体通常需人工标注或监督训练。本文提出TeQoDO：一种仅依靠大模型自身SQL编程能力，并结合提示中提供的模块化TOD系统概念，从零开始自动构建TOD本体的方法。实验表明，TeQoDO优于迁移学习方法，其构建的本体在下游对话状态追踪任务中具有竞争力。消融实验证明模块化系统概念的关键作用。此外，TeQoDO可扩展至更大规模本体构建，我们在维基百科和arXiv数据集上进行了探索。本工作被视为推动本体更广泛应用的重要一步。
原文摘要 · Abstract (English)
Large language models (LLMs) are widely used as general-purpose knowledge sources, but they rely on parametric knowledge, limiting explainability and trustworthiness. In task-oriented dialogue (TOD) systems, this separation is explicit, using an external database structured by an explicit ontology to ensure explainability and controllability. However, building such ontologies requires manual labels or supervised training. We introduce TeQoDO: a Text-to-SQL task-oriented Dialogue Ontology construction method. Here, an LLM autonomously builds a TOD ontology from scratch using only its inherent SQL programming capabilities combined with concepts from modular TOD systems provided in the prompt. We show that TeQoDO outperforms transfer learning approaches, and its constructed ontology is competitive on a downstream dialogue state tracking task. Ablation studies demonstrate the key role of modular TOD system concepts. TeQoDO also scales to allow construction of much larger ontologies, which we investigate on a Wikipedia and arXiv dataset. We view this as a step towards broader application of ontologies.
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。