检索结果-内蒙古大学图书馆

Negative sampling and rule mining for explainable link prediction in knowledge graphs

knowledge-BASED SYSTEMS 2022年第0期250卷

作者： Islam, Kamrul Aridhi, Sabeur Smail-Tabbone, Malika Univ Lorraine CNRS Inria LORIA F-54000 Nancy France

Several KG embedding methods were proposed to learn low dimensional vector representations of entities and relations of a KG. Such representations facilitate the link prediction task, in the service of inference and KG completion. In this context, it is important to achieve both an efficient KG embedding and explainable predictions. During learning of efficient embeddings, sampling negative triples was highlighted as an important step as KGs only have observed positive triples. We propose an efficient simple negative sampling (SNS) method based on the assumption that the entities which are closer in the embedding space to the corrupted entity are able to provide high-quality negative triples. As for explainability, it actually constitutes a thriving research question especially when it comes to analyze KGs with their rich semantics rooted in description logics. Hence, we propose in this paper a new rule mining method on the basis of learned embeddings. We extensively evaluate our proposals through several experiments. We evaluate our SNS sampling method plugged to several KG embedding models through link prediction task performances on well-known datasets. Experimental results show that the SNS improves the prediction performance of KG embedding models, and outperforms the existing sampling methods. To assess the performance of our rule mining method with and without SNS, we mine and evaluate rules on three popular datasets. The extracted rules are evaluated as knowledge nuggets extracted from the KG and also as support for explainable link prediction. The overall results are good and open the way to many improvements and new perspectives. (c) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge graph embedding Link prediction Negative sampling Rule mining Explainability

来源：评论

学校读者我要写书评

暂无评论

Combining embedding-based and symbol-based methods for entity alignment

引用

PATTERN RECOGNITION 2022年 124卷 108433-108433页

作者： Jiang, Tingting Bu, Chenyang Zhu, Yi Wu, Xindong Hefei Univ Technol Minist Educ Key Lab Knowledge Engn Big Data Hefei Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei Peoples R China Hefei Univ Technol Inst Big Knowledge Sci Hefei Peoples R China Yangzhou Univ Sch Informat Engn Yangzhou Jiangsu Peoples R China Mininglamp Technol Mininglamp Acad Sci Beijing Peoples R China

The objective of entity alignment is to judge whether entities refer to the same object in the real world. Methods for entity alignment can be grossly divided into two groups: conventional symbol-based entity alignment methods and embedding-based entity alignment methods. Both groups of methods have advantages and disadvantages (which are detailed in Section 1). Therefore, combining the advantages of both methods might be a promising strategy. However, to the best of our knowledge, only the RTEA algorithm that was proposed in our previous conference paper (Proceeding of Pacific Rim International Conference on Artificial Intelligence, pp. 162-175, 2019) utilizes this strategy for entity alignment. This manuscript is an extended version of that conference paper, in which an improved algorithm, namely, ESEA (combining embedding-based and symbol-based methods for entity alignment), is proposed based on the following steps. First, a novel method for combining embedding models with symbol-based models is proposed. Entities with high vector similarities are obtained through a hybrid embedding model, and the final aligned entity pairs are calculated via symbol-based methods. Second, a series of symbol based methods, instead of only the edit distance method in the original version, are combined with embedding-based methods for relation alignment. Third, we combine symbol-based and embedding based methods in a more complicated framework with the objective of better exploiting the advantages of both methods. The experimental results on real-world datasets demonstrate that the proposed method outperformed several state-of-the-art embedding-based entity alignment approaches and outperformed our previous RTEA method.(c) 2021 Elsevier Ltd. All rights reserved.

关键词： Entity alignment knowledge graph embedding String Similarity

来源：评论

学校读者我要写书评

暂无评论

LiterallyWikidata - A Benchmark for knowledge graph Completion Using Literals 20th

LiterallyWikidata - A Benchmark for Knowledge Graph Completi...

引用

20th International Semantic Web Conference (ISWC)

作者： Gesese, Genet Asefa Alam, Mehwish Sack, Harald FIZ Karlsruhe Leibniz Inst Informat Infrastruct Eggenstein Leopoldshafen Germany Karlsruhe Inst Technol Inst AIFB Karlsruhe Germany

ISBN: (纸本)9783030883614;9783030883607

In order to transform a knowledge graph (KG) into a low dimensional vector space, it is beneficial to preserve as much semantics as possible from the different components of the KG. Hence, some link prediction approaches have been proposed so far which leverage literals in addition to the commonly used links between entities. However, the procedures followed to create the existing datasets do not pay attention to literals. Therefore, this study presents a set of KG completion benchmark datasets extracted from Wikidata and Wikipedia, named LiterallyWikidata. It has been prepared with the main focus on providing benchmark datasets for multimodal KG embedding (KGE) models, specifically for models using numeric and/or text literals. Hence, the benchmark is novel as compared to the existing datasets in terms of properly handling literals for those multimodal KGE models. LiterallyWikidata contains three datasets which vary both in size and structure. Benchmarking experiments on the task of link prediction have been conducted on LiterallyWikidata with extensively tuned unimodal/multimodal KGE models. The datasets are available at https://***/10.5281/zenodo.4701190.

关键词： knowledge graph completion knowledge graph embedding Link prediction Literals Benchmark dataset

来源：评论

学校读者我要写书评

暂无评论

Representing knowledge graphs with Gaussian Mixture embedding 14th

Representing Knowledge Graphs with Gaussian Mixture Embeddin...

引用

14th International Conference on knowledge Science, Engineering, and Management (KSEM)

作者： Feng, Wenying Zha, Daren Guo, Xiaobo Dong, Yao He, Yuanye Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9783030821364;9783030821357

knowledge graph embedding (KGE) has attracted more and more attention and has been widely used in downstream AI tasks. Some proposed models learn the embeddings of knowledge graph (KG) into a low-dimensional continuous vector space by optimizing a customized loss function. However, these methods either ignore the polysemy of entities/relations in KG, or cannot model the uncertainty of them. Therefore, we propose KG2GM (knowledge graph to Gaussian Mixture), a density-based KGE method, for modeling the polysemy and uncertainty of KG simultaneously. Each entity/relation in KG is represented by a Gaussian mixture probability distribution. Each Gaussian component of the mixed distribution represents one kind of semantics, where the mean vector denotes its space position, and the covariance matrix denotes its uncertainty. In this way we can model the polysemy and uncertainty of KG simultaneously. We employ symmetrized KL divergence and EL (Expected Likelihood) to measure the component similarities and make their probabilistic combination as the score function of the triplet. We conduct experiments on link prediction with two benchmark datasets (WN18RR and FB15k-237). The results show that our method can effectively model the polysemy and uncertainty of entities and relations in KG.

关键词： knowledge graph embedding Gaussian Mixture Model Distributed representation knowledge graph completion Link prediction

来源：评论

学校读者我要写书评

暂无评论

Neural-Answering Logical Queries on knowledge graphs 21

Neural-Answering Logical Queries on Knowledge Graphs

引用

27th ACM SIGKDD International Conference on knowledge Discovery and Data Mining (KDD)

作者： Liu, Lihui Du, Boxin Ji, Heng Zhai, ChengXiang Tong, Hanghang Univ Illinois Dept Comp Sci Champaign IL 61820 USA

ISBN: (纸本)9781450383325

Logical queries constitute an important subset of questions posed in knowledge graph question answering systems. Yet, effectively answering logical queries on large knowledge graphs remains a highly challenging problem. Traditional subgraph matching based methods might suffer from the noise and incompleteness of the underlying knowledge graph, often with a prolonged online response time. Recently, an alternative type of method has emerged whose key idea is to embed knowledge graph entities and the query in an embedding space so that the embedding of answer entities is close to that of the query. Compared with subgraph matching based methods, it can better handle the noisy or missing information in knowledge graph, with a faster online response. Promising as it might be, several fundamental limitations still exist, including the linear transformation assumption for modeling relations and the inability to answer complex queries with multiple variable nodes. In this paper, we propose an embedding based method (NEWLOOK) to address these limitations. Our proposed method offers three major advantages. First (Applicability), it supports four types of logical operations and can answer queries with multiple variable nodes. Second (Effectiveness), the proposed NEWLOOK goes beyond the linear transformation assumption, and thus consistently outperforms the existing methods. Third (Efficiency), compared with subgraph matching based methods, NEWLOOK is at least 3 times faster in answering the queries;compared with the existing embedding based methods, NEWLOOK bears a comparable or even faster online response and offline training time.

关键词： knowledge graph query knowledge graph embedding Logical query embedding

来源：评论

学校读者我要写书评

暂无评论

CTEA: Context and Topic Enhanced Entity Alignment for knowledge graphs

引用

NEUROCOMPUTING 2020年 410卷 419-431页

作者： Yan, Zhihuan Peng, Rong Wang, Yaqian Li, Weidong Wuhan Univ Sch Comp Sci Wuhan Peoples R China

We study the problem of finding entities referring to the same real world object in multilingual knowledge graphs(KGs), i.e., entity alignment for multilingual KGs. Recently, embedding-based entity alignment methods get extended attention in this area. Most of them firstly embed the entities in low dimensional vectors space via relation structure of entities, and then align entities via these learned embeddings combined with some entity similarity function. Even achieved promising performances, these methods are defective in utilizing entity contexts and entity topic information. In this paper, we propose a novel entity alignment framework CTEA (Context and Topic Enhanced Entity Alignment), which integrates entity context information and entity topic information to help alignment. This framework learns entity topic distributions from their attributes with a specially designed topic model BTM4EA, and the learned entity topic distributions are used to filter some weakly correlated entities for each entity to be aligned. Meanwhile, we embed KGs to low dimensional vectors space via translation-based KG embedding model and mine context information from these vectors with an attention attached Convolutional Neural Network(CNN). The entity embeddings, entity contexts and entity topics are combined to get the final alignment results. Extended experiments reveal that our method achieves promising performances in most cases. (C) 2020 Published by Elsevier B.V.

关键词： knowledge graph embedding Entity alignment Entity contexts Topic model

来源：评论

学校读者我要写书评

暂无评论

CODER: knowledge-infused cross-lingual medical term embedding for term normalization

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2022年 126卷 103983-103983页

作者： Yuan, Zheng Zhao, Zhengyun Sun, Haixia Li, Jiao Wang, Fei Yu, Sheng Tsinghua Univ Ctr Stat Sci Weiqinglou Rm 209 Beijing 100084 Peoples R China Tsinghua Univ Dept Ind Engn Beijing Peoples R China Chinese Acad Med Sci Inst Med Informat Peking Union Med Coll Beijing Peoples R China Cornell Univ Weill Cornell Med Coll Dept Populat Hlth Sci Ithaca NY 14853 USA

Objective: This paper aims to propose knowledge-aware embedding, a critical tool for medical term normalization. Methods: We develop CODER (Cross-lingual knowledge-infused medical term embedding) via contrastive learning based on a medical knowledge graph (KG) named the Unified Medical Language System, and similarities are calculated utilizing both terms and relation triplets from the KG. Training with relations injects medical knowledge into embeddings and can potentially improve their performance as machine learning features. Results: We evaluate CODER based on zero-shot term normalization, semantic similarity, and relation classifi-cation benchmarks, and the results show that CODER outperforms various state-of-the-art biomedical word embeddings, concept embeddings, and contextual embeddings. Conclusion: CODER embeddings excellently reflect semantic similarity and relatedness of medical concepts. One can use CODER for embedding-based medical term normalization or to provide features for machine learning. Similar to other pretrained language models, CODER can also be fine-tuned for specific tasks. Codes and models are available at https://***/GanjinZero/CODER.

关键词： Medical term normalization Cross-lingual Medical term representation knowledge graph embedding Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Translational relation embeddings for multi-hop knowledge base question answering

引用

JOURNAL OF WEB SEMANTICS 2022年第0期74卷

作者： Li, Ziyan Wang, Haofen Zhang, Wenqiang Fudan Univ Acad Engn & Technol Shanghai Peoples R China Tongji Univ Coll Design & Innovat Shanghai Peoples R China

Multi-hop knowledge Base Question Answering (KBQA) aims to predict answers that require multi-hop reasoning from the topic entity in the question over the knowledge Base (KB). Relation extraction is a core step in KBQA, which extracts the relation path from the topic entity to the answer entity. Compared with single-hop questions, multi-hop ones have more complex syntactic structures to understand, and multi-hop relation paths lead to a larger search space, which makes it much more challenging to extract the correct relation paths. To tackle the above challenges, most existing relation extraction approaches focus on the semantic similarity between questions and relation paths. However, those approaches only consider the word semantics of the relation names but ignore the graph semantics inside the knowledge base. As a result, their generalization ability relying on the naming rules of the relations, making it more difficult to generalize over large knowledge bases. To address the current limitations and take advantage of the graph semantics of relations, we propose a novel translational embedding-based relation extractor that utilizes pretrained embeddings from TransE. In particular, we treat the multi-hop relation path as a translation from the first relation to the last one in the semantic space of TransE. Then we map the question into this space under the supervision of the path embeddings. To take full advantage of the pretrained graph semantics in TransE, we propose a KBQA framework that leverages pretrained relation semantics in relation extraction and pretrained entity semantics in answer selection. Our approach achieves state-of-the-art performance on two benchmark datasets, WebQuestionSP and MetaQA, demonstrating its effectiveness on the multi-hop KBQA task. (C) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge base question answering knowledge graph embedding Multi-hop relation extraction

来源：评论

学校读者我要写书评

暂无评论

Causality-aware Enhanced Model for Multi-hop Question Answering over knowledge graphs

引用

knowledge-BASED SYSTEMS 2022年 250卷

作者： Sui, Yuan Feng, Shanshan Zhang, Huaxiang Cao, Jian Hu, Liang Zhu, Nengjun Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Shandong JiaoTong Univ Jinan Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Tongji Univ DeepBlue Acad Sci Sch Elect & Informat Engn Shanghai Peoples R China DeepBlue Acad Sci Shanghai Peoples R China Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China

To improve the performance of knowledge graph-based question answering system (KGQA), several approaches have been developed to construct a semantic parser based on entity linking, relation identification and logical/numerical structure identification. However, existing methods arrive at answers only by maximizing the data likelihood only on the sparse or imbalanced explicit relations, ignoring the potentially large number of latent relations. It makes KGQA suffer from a high level of spurious entity relations and missing link challenge. In this paper, we propose a causal filter (CF) model for KGQA (CF-KGQA), which performs causal interference on the relation representation space to reduce the spurious relation representation in a data-driven manner, i.e., the goal of this work is to comprehensively discover disentangled latent factors to alleviate the spurious correlation problem in KGQA. The model comprises a causal pairwise aggregator (A(P)) and a disentangled latent factor aggregator (A(C)). The former filters out most spurious entity relations inconsistent to their dense groups' neighborhood, and generates a causal pairwise matrix among all the candidate relations. The latter learns the latent relation representation via an encoder-decoder on the causal pairwise matrix. It disconnects the latent factor and the causal confounder beneath the knowledge embedding space by causal intervention. To prove the effectiveness and efficiency of the proposed approach, we test CFKGQA and other state-of-the-art methods on four public real-world datasets. The experiments indicate that our approach outperforms the recent methods and is also less sensitive to the spurious correlation problem, thus demonstrating the robustness of CF-KGQA. (C) 2022 Published by Elsevier B.V.

关键词： knowledge graph-based question answering Causal representation learning Constraint pairwise-based clustering knowledge graph embedding Confounding bias

来源：评论

学校读者我要写书评

暂无评论

embedding Dynamic knowledge graphs based on Observational Ontologies in Semantic Vector Spaces

Embedding Dynamic Knowledge Graphs based on Observational On...

引用

Conference on Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III

作者： Millar, Declan Braines, Dave D'Arcy, Laura Barclay, Iain Summers-Stay, Doug Cripps, Paul IBM Res Europe Hursley England Cardiff Univ Sch Comp Sci & Informat Cardiff Wales US Army Res Lab Adelphi MD USA Def Sci & Technol Lab Salisbury Wilts England

ISBN: (数字)9781510643307

ISBN: (纸本)9781510643307

knowledge graphs (KGs) provide a useful representation format for capturing complex knowledge about an information domain, with rich logical descriptions available for defining the relationships between entities. Separately, semantic vector spaces (SVSs) capture the relative meanings of terms based on their actual usage within a dataset and allow useful operations for exploring the relationships between these terms. Combining KGs and SVSs via knowledge graph embedding (KGE) enables further analysis tasks to leverage learned semantic vectors to gain additional insights. Therefore, KGE represents an interesting and potentially powerful tool for identifying emergent or unexpected behavior, or for seeking previously unaccounted for relationships, event, and groups. In this work, we report on the state-of-the-art in KGE. We describe the operational benefits that can be gained from this approach and the considerations that apply for observational ontologies that describe a complex, untrusted, time-sensitive, and rapidly-evolving environment. We suggest several promising avenues for future research in this context.

关键词： Semantic vector spaces knowledge graphs knowledge graph embedding Observational ontologies

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：