arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.06206cs.CLcs.SI
收藏

SQUIRE:一种多跳知识图谱推理的Sequence-to-Sequence框架

SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning

Tsinghua University(清华大学);Alibaba Group(阿里巴巴集团)

Yushi Bai, Xin Lv, Juanzi Li, Lei Hou, Yincen Qu, Zelin Dai, Feiyu Xiong

摘要:

多跳知识图谱(KG)推理近年来得到了广泛的研究,以提供可解释的预测与证据路径的丢失链接。大多数以前的作品使用基于强化学习(RL)的方法,学习导航到目标实体的路径。然而,这些方法收敛速度慢,收敛性差,并且当路径上有缺失边时,它们可能无法推断出特定路径。在这里,我们提出了SQUIRE,第一个基于序列到序列的多跳推理框架,它利用编码器-解码器Transformer结构将查询转换为路径。我们的框架带来了两个好处:(1)它可以以端到端的方式学习和预测,这提供了更好和更快的收敛;(2)我们的Transformer模型不依赖于现有的边缘来生成路径,并且具有沿着路径完成缺失边缘的灵活性,特别是在稀疏KG中。在标准和稀疏KG上的实验表明,我们的方法比以前的方法有显着的改进,同时收敛速度快4 - 7倍。

英文摘要:

Multi-hop knowledge graph (KG) reasoning has been widely studied in recent years to provide interpretable predictions on missing links with evidential paths. Most previous works use reinforcement learning (RL) based methods that learn to navigate the path towards the target entity. However, these methods suffer from slow and poor convergence, and they may fail to infer a certain path when there is a missing edge along the path. Here we present SQUIRE, the first Sequence-to-sequence based multi-hop reasoning framework, which utilizes an encoder-decoder Transformer structure to translate the query to a path. Our framework brings about two benefits: (1) It can learn and predict in an end-to-end fashion, which gives better and faster convergence; (2) Our Transformer model does not rely on existing edges to generate the path, and has the flexibility to complete missing edges along the path, especially in sparse KGs. Experiments on standard and sparse KGs show that our approach yields significant improvement over prior methods, while converging 4x-7x faster.

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。

↑