Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases

Weikum, Gerhard; Dong, Luna; Razniewski, Simon; Suchanek, Fabian M.

doi:10.48550/arxiv.2009.11564

Cited by 7 publications

(11 citation statements)

References 424 publications

(605 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge Graph (KG) is widely used for representing graph structured knowledge, and has achieved great success in many domains, such as search engine, recommendation system, clinic AI, personal assistant and natural language understanding [75,133,194]. In this part, we first describe what is a KG from the Semantic Web perspective, and then introduce other KG definitions that are widely used in different domains such as CV and NLP.…”

Section: Definition and Scopementioning

confidence: 99%

Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey

Chen¹,

Geng²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning methods especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for training. In real-world applications, we often need to address sample shortage due to e.g., dynamic contexts with emerging prediction targets and costly sample annotation. Therefore, low-resource learning, which aims to learn robust prediction models with no enough resources (especially training samples), is now being widely investigated. Among all the low-resource learning studies, many prefer to utilize some auxiliary information in the form of Knowledge Graph (KG), which is becoming more and more popular for knowledge representation, to reduce the reliance on labeled samples. In this survey, we very comprehensively reviewed over 90 papers about KG-aware research for two major low-resource learning settings -zero-shot learning (ZSL) where new classes for prediction have never appeared in training, and few-shot learning (FSL) where new classes for prediction have only a small number of labeled samples that are available. We first introduced the KGs used in ZSL and FSL studies as well as the existing and potential KG construction solutions, and then systematically categorized and summarized KG-aware ZSL and FSL methods, dividing them into different paradigms such as the mapping-based, the data augmentation, the propagation-based and the optimization-based. We next presented different applications, including not only KG augmented prediction tasks in Computer Vision and Natural Language Processing (e.g., image classification, visual question answering, text classification and knowledge extraction), but also tasks for KG curation (e.g., inductive KG completion), and some typical evaluation resources for each task. We eventually discussed some challenges and future directions on aspects such as new learning and reasoning paradigms, and the construction of high quality KGs.

show abstract

Section: Definition and Scopementioning

confidence: 99%

Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey

Chen¹,

Geng²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Knowledge [24][25][26] is generally recorded in logically organized language containing subjects, predicates, and objects related to objective facts in the world. Among them, subjects and objects are termed as entities, the abstract or concrete things of fiction or reality with special types and attributes.…”

Section: Informationmentioning

confidence: 99%

“…Knowledge graphs [24] can convert knowledge into a machine-readable form by firstly organizing the entities (i.e., subjects and objects) and relations (i.e., predicates) extracted from knowledge into triplets (subject, predicate, object). Specifically, let E denote the set of subjects and objects, let R denote the set of predicates, knowledge can be represented with triplets S = (h, r, t), where h ∈ E is the head entity (i.e., subject) and t ∈ E is the tail entity (i.e., object), r ∈ R is a directed edge from h to t. Following the process illustrated in Fig.…”

Section: Graph Representationsmentioning

confidence: 99%

“…Consequently, inadequate user-item interactions out of the sparsity and cold start problems weaken the accuracy of inference for user preference by recommendation models; thus defend recommendation performance. As for tackling the sparsity and cold start problems, employing side information [22,23] and knowledge [24][25][26] (Sec. 2.1.1 gives details) as a supplement to user-item interactions in order to uncover hidden (indirect) user-item relations enriching observed information for the recommendation has been proven promising recently.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recommender systems based on graph embedding techniques: A comprehensive review

Deng

2021

Preprint

View full text Add to dashboard Cite

Recommender systems, a pivotal tool to alleviate the information overload problem, aim to predict user's preferred items from millions of candidates by analyzing observed user-item relations. As for tackling the sparsity and cold start problems encountered by recommender systems, uncovering hidden (indirect) user-item relations by employing side information and knowledge to enrich observed information for the recommendation has been proven promising recently; and its performance is largely determined by the scalability of recommendation models in the face of the high complexity and large scale of side information and knowledge. Making great strides towards efficiently utilizing complex and large-scale data, research into graph embedding techniques is a major topic. Equipping recommender systems with graph embedding techniques contributes to outperforming the conventional recommendation implementing directly based on graph topology analysis and has been widely studied these years. This article systematically retrospects graph embedding-based recommendation from embedding techniques for bipartite graphs, general graphs, and knowledge graphs, and proposes a general design pipeline of that. In addition, comparing several representative graph embedding-based recommendation models with the most common-used conventional recommendation models, on simulations, manifests that the conventional models overall outperform the graph embedding-based ones in predicting implicit user-item interactions, revealing the relative weakness of graph embedding-based recommendation in these tasks. To foster future research, this article proposes constructive suggestions on making a trade-off between graph embedding-based recommendation and the conventional recommendation in different tasks as well as some open questions.

show abstract

“…Knowledge bases (KBs) are data structures that connect pairs of entities or concepts by semantically meaningful symbolic relations. Decades' worth of research have been invested into using KBs as tools for relational world knowledge representation in machines (Minsky, 1974;Sowa, 1992;Lenat, 1995;Miller, 1998;Liu and Singh, 2004;Suchanek et al, 2007;Bollacker et al, 2008;Vrandečić and Krötzsch, 2014;Dong et al, 2014;Speer et al, 2017;Ammar et al, 2018;Weikum et al, 2020;Hwang et al, 2021;Ilievski et al, 2021b;Hope et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Relational World Knowledge Representation in Contextual Language Models: A Review

Safavi¹,

Koutra²

2021

Preprint

View full text Add to dashboard Cite

Relational knowledge bases (KBs) are established tools for world knowledge representation in machines. While they are advantageous for their precision and interpretability, they usually sacrifice some data modeling flexibility for these advantages because they adhere to a manually engineered schema. In this review, we take a natural language processing perspective to the limitations of KBs, examining how they may be addressed in part by training neural contextual language models (LMs) to internalize and express relational knowledge in free-text form. We propose a novel taxonomy for relational knowledge representation in contextual LMs based on the level of KB supervision provided, considering both works that probe LMs for implicit relational knowledge acquired during self-supervised pretraining on unstructured text alone, and works that explicitly supervise LMs at the level of KB entities and/or relations. We conclude that LMs and KBs are complementary representation tools, as KBs provide a high standard of factual precision which can in turn be flexibly and expressively modeled by LMs, and provide suggestions for future research in this direction.

show abstract

Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases

Cited by 7 publications

References 424 publications

Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey

Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey

Recommender systems based on graph embedding techniques: A comprehensive review

Relational World Knowledge Representation in Contextual Language Models: A Review

Contact Info

Product

Resources

About