用三步法融合语言模型与知识图谱，提升简单问答准确率
Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering
- 分三步处理：实体识别、关系预测、图查询
- 关系预测阶段结合分类与排序，效果优于其他方法
- 对罕见实体也表现稳健，适合需要高可靠性的场景
尽管简单问题如“灰姑娘的作者是谁”是常见题型，但至今仍未完全解决。令人惊讶的是，即使最先进的大语言模型在处理这类问题时仍易出错，尤其面对罕见实体时。由于答案通常仅需一步关联到问题实体，可借助结构化知识图谱（KG）来回答。本文提出Konstruktor——一种高效且鲁棒的方法，将问题分解为三步：(i) 实体提取与链接，(ii) 关系预测，(iii) 查询知识图谱。该方法融合语言模型的泛化能力与知识图谱的可解释性。我们在两种命名实体识别与链接方法及多种关系检测技术上进行实验。结果表明，在流程中最具挑战性的关系预测环节，结合关系分类/生成与排序的方法优于其他方案。在四个数据集上均取得强性能。
原文摘要 · Abstract (English)
While being one of the most popular question types, simple questions such as "Who is the author of Cinderella?", are still not completely solved. Surprisingly, even the most powerful modern Large Language Models are prone to errors when dealing with such questions, especially when dealing with rare entities. At the same time, as an answer may be one hop away from the question entity, one can try to develop a method that uses structured knowledge graphs (KGs) to answer such questions. In this paper, we introduce Konstruktor - an efficient and robust approach that breaks down the problem into three steps: (i) entity extraction and entity linking, (ii) relation prediction, and (iii) querying the knowledge graph. Our approach integrates language models and knowledge graphs, exploiting the power of the former and the interpretability of the latter. We experiment with two named entity recognition and entity linking methods and several relation detection techniques. We show that for relation detection, the most challenging step of the workflow, a combination of relation classification/generation and ranking outperforms other methods. We report Konstruktor's strong results on four 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。