arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.04174cs.CLcs.AI
收藏

通过从决策中解耦特征学习的可解释和低资源实体匹配

Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

Tsinghua University(清华大学);University of Bonn(波恩大学);Alibaba Group(阿里巴巴集团)

Zijun Yao, Chengjiang Li, Tiansi Dong, Xin Lv, Jifan Yu, Lei Hou, Juanzi Li, Yichi Zhang, Zelin Dai

摘要:

实体匹配(Entity Matching,EM)的目的是识别表示相同真实世界对象的实体记录。神经EM模型学习实体描述的向量表示,并端到端匹配实体。虽然这些方法很强大,但需要许多资源进行训练,并且缺乏可解释性。在本文中,我们提出了一种新的EM框架,由异构信息融合(HIF)和关键属性树(KAT)归纳解耦的特征表示匹配决策。在预训练语言建模中使用自监督学习和掩码机制,HIF通过对未标记数据的属性间注意来学习噪声属性值的嵌入。使用一组比较功能和有限数量的注释数据,KAT归纳学习一个有效的决策树,可以通过生成实体匹配规则,其结构是由领域专家主张解释。在6个公共数据集和3个工业数据集上的实验表明,该方法是高效的,在大多数情况下优于SOTA EM模型。我们的代码和数据集可以从https://github.com/THU-KEG/HIF-KAT获得。

英文摘要:

Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. Neural EM models learn vector representation of entity descriptions and match entities end-to-end. Though robust, these methods require many resources for training, and lack of interpretability. In this paper, we propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction to decouple feature representation from matching decision. Using self-supervised learning and mask mechanism in pre-trained language modeling, HIF learns the embeddings of noisy attribute values by inter-attribute attention with unlabeled data. Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts. Experiments on 6 public datasets and 3 industrial datasets show that our method is highly efficient and outperforms SOTA EM models in most cases. Our codes and datasets can be obtained from https://github.com/THU-KEG/HIF-KAT.

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。

↑