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.
ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning
School of Computer Science, Hubei University(湖北大学计算机学院);School of Cyber Science and Technology, Hubei University(湖北大学网络空间安全学院);Institute of Vocational Education, Guangdong Industry Polytechnic University(广东轻工职业技术学院职业教育学院);School of Computer Science, Hubei Key Laboratory of Big Data Intelligent Analysis and Application, Hubei University(湖北大学计算机学院、湖北省大数据智能分析与应用重点实验室)
Interpretable Entity Representations through Large-Scale Typing
Department of Computer Science(计算机科学系);The University of Texas at Austin(德克萨斯大学奥斯汀分校)
在用于自然语言处理的标准方法中,文本中的实体通常被嵌入具有预训练模型的密集向量空间中。以这种方式产生的嵌入在输入到下游模型时是有效的,但它们需要最终任务的微调,并且从根本上难以解释。在本文中,我们提出了一种方法来创建实体表示,是人类可读的,并实现高性能的实体相关的任务开箱即用。我们的表示是向量,其值对应于细粒度实体类型的后验概率,表示类型模型决定实体属于相应类型的置信度。我们使用细粒度实体类型化模型获得这些表示,该模型在监督的超细实体类型化数据(Choi et al. 2018)或来自维基百科的远程监督示例上进行训练。在涉及识别实体身份的实体探测任务中,我们在无参数下游模型中使用的嵌入在训练模型中与基于ELMo和BERT的嵌入相比具有竞争力的性能。我们还表明,它是可能的,以减少我们的类型集的大小在特定领域的学习为基础的方式。最后,我们表明,这些嵌入可以事后修改,通过少量的规则,将领域知识和提高性能。
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
School of Information Science and Engineering, Yunnan University(云南大学信息科学与工程学院);School of Software, Yunnan University(云南大学软件学院);National University of Singapore(新加坡国立大学);School of Engineering, Yunnan University(云南大学工程学院)
LiteInception: A Lightweight and Interpretable Deep Learning Framework for General Aviation Fault Diagnosis
Hangzhou International Innovation Institute, Beihang University(北京航空航天大学杭州国际创新研究院);Science and Technology on Complex Aviation System Simulation Laboratory(复杂航空系统仿真重点实验室);The First Aircraft Institute of Aviation Industry Corporation of China(中国航空工业集团公司第一飞机设计研究院);School of Reliability and Systems Engineering, Beihang University(北京航空航天大学可靠性与系统工程学院)
A Decoupling and Aggregating Framework for Joint Extraction of Entities and Relations
Japan Advanced Institute of Science and Technology(日本先进科学技术学院);National Institute of Advanced Industrial Science and Technology(国立先进工业科学技术研究院);University of Tsukuba(筑波大学)
MedPath: Multi-Domain Cross-Vocabulary Hierarchical Paths for Biomedical Entity Linking
Department of Medical Informatics, Amsterdam UMC, University of Amsterdam, The Netherlands(阿姆斯特丹大学医学信息学系,阿姆斯特丹大学医学中心,荷兰);Amsterdam Public Health, Methodology, Amsterdam, The Netherlands(阿姆斯特丹公共卫生,方法学,阿姆斯特丹,荷兰);ILLC, University of Amsterdam, The Netherlands(阿姆斯特丹大学ILLC,荷兰)
Linguistic Features for Interpretable Textual Entailment
Centro de Investigación en Ciencias, Universidad Autónoma del Estado de Morelos(莫雷洛斯州自治大学科学研究中心);Centro Interdisciplinario de Investigación en Humanidades, Universidad Autónoma del Estado de Morelos(莫雷洛斯州自治大学跨学科人文研究中心)