Abstract
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs). The core challenge of this task lies in understanding the complex semantic information regarding multiple types of time constraints (e.g., before, first) in questions. Existing end-to-end methods implicitly model the time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively. Motivated by semantic-parsing-based approaches that explicitly model constraints in questions by generating logical forms with symbolic operators, we design fundamental temporal operators for time constraints and introduce a novel self-improvement Programming method for TKGQA (Prog-TQA). Specifically, Prog-TQA leverages the in-context learning ability of Large Language Models (LLMs) to understand the combinatory time constraints in the questions and generate corresponding program drafts with a few examples given. Then, it aligns these drafts to TKGs with the linking module and subsequently executes them to generate the answers. To enhance the ability to understand questions, Prog-TQA is further equipped with a self-improvement strategy to effectively bootstrap LLMs using high-quality self-generated drafts. Extensive experiments demonstrate the superiority of the proposed Prog-TQA on MultiTQ and CronQuestions datasets, especially in the Hits@1 metric.
Abstract (translated)
Temporal Knowledge Graph Question Answering (TKGQA) 的目标是回答具有时间意图的问题,而不仅仅是 Temporal Knowledge Graphs (TKGs)。这项任务的核心挑战在于理解关于多种时间约束(如 before、first)的复杂语义信息。现有的端到端方法通过学习问题及其候选答案的时间感知嵌入来暗示时间约束,但并未真正理解问题。受到语义解析方法(如通过生成逻辑形式使用符号操作来建模问题约束)的启发,我们设计基本的时间约束操作,并引入了一种名为 Self-Improvement Programming Method for TKGQA (Prog-TQA) 的自改进方法。 具体来说,Prog-TQA 利用大型语言模型的上下文学习能力来理解问题中的可组合时间约束,并生成几个示例后的程序草案。然后,它将草案对齐到 TKGs,并使用链接模块执行它们以生成答案。为了增强理解问题的能力,Prog-TQA 还配备了自改进策略,通过使用高质量的自生成草案有效地启动大型语言模型。大量实验证明,与 MultiTQ 和 CronQuestions 数据集相比,Prog-TQA 在 Hits@1 指标上具有优越性。
URL
https://arxiv.org/abs/2404.01720