arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06378cs.CLcs.LG
收藏

QA-GNN:基于语言模型和知识图谱的问答推理

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

Stanford University(斯坦福大学)

Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec

摘要:

使用来自预训练的语言模型(LM)和知识图谱(KG)的知识来回答问题的问题提出了两个挑战:给定QA上下文(问题和答案选择),方法需要(i)从大型KG中识别相关知识,以及(ii)在QA上下文和KG上执行联合推理。在这项工作中,我们提出了一个新的模型,QA-GNN,它通过两个关键的创新来解决上述挑战:(i)相关性评分,我们使用LM来估计KG节点相对于给定QA上下文的重要性,以及(ii)联合推理,我们将QA上下文和KG连接起来形成一个联合图,并通过图神经网络相互更新它们的表示。我们在常识(CommonsenseQA,OpenBookQA)和生物医学(MedQA-USMLE)领域的QA基准上评估我们的模型。QA-GNN优于现有的LM和LM+KG模型,并表现出执行可解释和结构化推理的能力,例如,正确处理疑问句中的否定。

英文摘要:

The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. In this work, we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph neural networks. We evaluate our model on QA benchmarks in the commonsense (CommonsenseQA, OpenBookQA) and biomedical (MedQA-USMLE) domains. QA-GNN outperforms existing LM and LM+KG models, and exhibits capabilities to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑