Knowledge representation learning with entity descriptions, hierarchical types, and textual relations

Tang, Xing; Chen, Ling; Jun, Cui; Wei, Baogang

doi:10.1016/j.ipm.2019.01.005

Cited by 52 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Textual mentions refer to the individual sentence containing the entity pairs which are derived from ClueWeb. The sentence is processed with the dependency parser and represented as lexicalized dependency paths in [43] and [44]. Then the path, which contains words and dependency arcs, is defined as the textual relation between the entity pair.…”

Section: ) Textual Mentionsmentioning

confidence: 99%

“…However, the textual relation probably exists in multiple textual mentions containing the same entity pair and it is essential to figure out which better expresses the relation. Tang et al [43] propose Multi-source Knowledge Representation Learning (MKRL), introducing the position embedding and attention mechanism [52] in CNN to encode the lexicalized dependency paths extracted from the textual mentions. For the i th word in the path, position embedding x ih and x it is defined as the relative distance to the head entity and the tail entity from the word.…”

Section: ) Convolutional Neural Networkmentioning

confidence: 99%

“…FB15k-237-OWE is generated based on the FB15k-237 [62] in which redundant inverse relations have been removed and the entity descriptions are restricted in 5 words on average. [46] and MKRL [43]. The former does not share the details of model and the latter introduces entity type as auxiliary information besides texts.…”

Section: Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Utilizing Textual Information in Knowledge Graph Embedding: A Survey of Methods and Applications

Cong

Huang

2020

IEEE Access

View full text Add to dashboard Cite

Techniques that map the entities and relations of the knowledge graph (KG) into a low-dimensional continuous space are called KG embedding or knowledge representation learning. However, most existing techniques learn the embeddings based on the facts in KG alone, suffering from the issues of imperfection and spareness of KG. Recently, the research on textual information in KG embedding has attracted much attention due to the rich semantic information supplied by the texts. Thus, in this paper, a survey of techniques for textual information based KG embedding is proposed. Firstly, we introduce the techniques for encoding the textual information to represent the entities and relations from perspectives of encoding models and scoring functions, respectively. Secondly, methods for incorporating the textual information in the existing embedding techniques are summarized. Thirdly, we discuss the training procedure of textual information based KG embedding techniques. Finally, applications of KG embedding with textual information in the specific tasks such as KG completion in zero-shot scenario, multilingual entity alignment, relation extraction and recommender system are explored. We hope that this survey will give insights to researchers into textual information based KG embedding. INDEX TERMS Knowledge graph embedding, textual information, text-based embedding, text-improved embedding, embedding-based applications.

show abstract

Section: ) Textual Mentionsmentioning

confidence: 99%

Section: ) Convolutional Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Utilizing Textual Information in Knowledge Graph Embedding: A Survey of Methods and Applications

Cong

Huang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…concepts. Similarly, an order describing a work process and a written text describing the same sequence of operations will be represented in a similar way in a knowledge representation system (Xing Tang et al, 2019 ) . This is called representation of the meaning of a document or semantic representation.A semantic representation is an image of the mental model of knowledge derived from the peculiarities of the format chosen to present the information (Zhenyong Wu et al, 2016).…”

Section: Information and Knowledgementioning

confidence: 99%

Organisation of Knowledge From Traces of Human Learning

Mbaye¹

2019

Proceedings of the International Conference on E-Learning 2019

View full text Add to dashboard Cite

Faced with the diversity and the large number of learning resources available on e-learning platforms, learners often face problems of inadequacy between the training path to choose and the skills sought. Indeed, many learning platforms with recommendation exist, but these do not often include information and different characteristics of learners. This problem can be mitigated by the semantisation of the content and the organization of the knowledge of the different actors involved on the learning platform. In this paper, we make a modeling of the knowledge representation (thesauri and concept maps) of learning resources, based on information from learner's written records on a learning platform and knowledge modeling from expert interactions on resource and learner assessments. These models make it possible to represent knowledge from written tracesthese written traces are metadata resulting from the interactions made on a learning platform by the learners and the experts (for example the expert in charge of the content of the trainings, the expert in charge of the evaluation of the trainings carried out).

show abstract

“…binary linkage (Boutell et al, 2004), classifier chains (Read et al, 2011), label powerset (Tsoumakas et al, 2011), rankings by pairwise comparison (Hüllermeier et al, 2008;Fürnkranz et al, 2008). These developments have expanded the focus in textual processing from title searches and tagging (Hu et al, 2006) to multiple tag interactions (Murthy and Gross, 2017;Al-Salemi et al, 2019;Tang et al, 2019), complex text interlinkages for result caching (Kucukyilmaz et al, 2017), deep textual semantic interactions (Kastrati et al, 2019), and attempts to identify sentiments through textual recurrence (Abdi et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Machine learning classification of entrepreneurs in British historical census data

Montebruno

Bennett

Smith

et al. 2020

Information Processing & Management

View full text Add to dashboard Cite

Thanks to recent data availability, digitized transcriptions of Victorian censuses provide unprecedented historical big data on individuals in the past, but also with new methodological challenges like the classification of otherwise underreported entrepreneurs among a population sample of millions of individuals. This paper presents a methodological solution to accomplish the task of classifying entrepreneurs. We apply machine learning, including deep learning, to outperform a standard logistic regression algorithm. Our methodological developments traverse traditional disciplinary lines using state-of-the-art artificial intelligence methods. The main conclusion of the paper is that significant gains in performance can be achieved with historical archive data through machine learning to test economic theories on historical entrepreneurship. This suggests applicability to other disciplines in information sciences.

show abstract

Knowledge representation learning with entity descriptions, hierarchical types, and textual relations

Cited by 52 publications

References 6 publications

Utilizing Textual Information in Knowledge Graph Embedding: A Survey of Methods and Applications

Utilizing Textual Information in Knowledge Graph Embedding: A Survey of Methods and Applications

Organisation of Knowledge From Traces of Human Learning

Machine learning classification of entrepreneurs in British historical census data

Contact Info

Product

Resources

About