Multi-Cultural Interlinking of Web Taxonomies with ACROSS

Arantes, Mariana; Figueiredo, Flávio; Almeida, Jussara M.

doi:10.1561/106.00000011

Cited by 3 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For ontologies and on the semantic web, added complexity comes from taxonomies and ontological constraints [11,40]. Approaches to ontology alignment include BLOOMS [20] and PARIS [44], voting-based aggregation [49], probabilistic frameworks [32], or methods for the alignment of multicultural data [4]. These methods typically rely on a combination of lexical, structural, constraint and instance based information.…”

Section: Related Workmentioning

confidence: 99%

“…We use four popular general purpose KBs: (i) DBpedia raw extraction [2], (ii) DBpedia mapping-based extraction 4 [24], (iii) Wikidata truthy 5 [47] and (iv) Freebase 6 [5]. We analyze each KB in terms of predicate coverage.…”

Section: Kbs Usedmentioning

confidence: 99%

“…While there is a rich body of research on ontology alignment and schema matching [36,11,40,20,44,49,32,4], these works typically focus on identifying perfectly matching pairs of predicates with the same or largely overlapping values. This situation differs from our setting where the integer values of counting predicates and the cardinalities of enumerating predicates modelling the same or related phenomenon rarely match perfectly.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Uncovering Hidden Semantics of Set Information in Knowledge Bases

Ghosh¹,

Razniewski²,

Weikum³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often represented in two formats: (i) via counting predicates such as numberOfChildren and staffSize, that store aggregated integers, and (ii) via enumerating predicates such as parentOf and worksFor, that store individual set memberships. Both formats are typically complementary: unlike enumerating predicates, counting predicates do not give away individuals, but are more likely informative towards the true set size, thus this coexistence could enable interesting applications in question answering and KB curation.In this paper we aim at uncovering this hidden knowledge. We proceed in two steps. (i) We identify set-valued predicates from a given KB predicates via statistical and embedding-based features. (ii) We link counting predicates and enumerating predicates by a combination of co-occurrence, correlation and textual relatedness metrics. We analyze the prevalence of count information in four prominent knowledge bases, and show that our linking method achieves up to 0.55 F1 score in set predicate identification versus 0.40 F1 score of a random selection, and normalized discounted gains of up to 0.84 at position 1 and 0.75 at position 3 in relevant predicate alignments. Our predicate alignments are showcased in a demonstration system available at https://counqer.mpi-inf.mpg.de/spo.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Kbs Usedmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Uncovering Hidden Semantics of Set Information in Knowledge Bases

Ghosh¹,

Razniewski²,

Weikum³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to bring the run times down while performing exact reasoning, we study two seeding strategies. This paper is an extended version of our conference paper (Boldyrev et al, 2016), which focused on: dening and modeling the alignment problem for multicultural knowledge taxonomies, utilizing a taxonomy mediation source for category assignment of culture-independent semantic labels, and developing an eective algorithm for computing alignments based on the semantic labels, using integer optimization.…”

Section: Approach and Contributionmentioning

confidence: 99%

“…In addition to the contributions of our preliminary work (Boldyrev et al, 2016), this manuscript addresses the following: studying dierent seeding strategies for bringing the runtimes down for exact reasoning with two types of constraints, without sacricing the quality of the alignment; a comprehensive experimental study with user assessments for alignments between a variety of KB pairs: analyzing linkings produced by ACROSS with respect to concepts with high and low spelling differences. We demonstrate that ACROSS is able to cover more cases, where relying on syntactic similarity or translation fails; performing sensitivity study of linking with respect to the taxonomic levels.…”

Section: Approach and Contributionmentioning

confidence: 99%

Multi-Cultural Interlinking of Web Taxonomies with ACROSS

Boldyrev

Spaniol²,

Weikum

2018

JWS

Self Cite

View full text Add to dashboard Cite

The Web hosts a huge variety of multi-cultural taxonomies. They encompass product catalogs of e-commerce, general-purpose knowledge bases and numerous domain-specic category systems. The enormous heterogeneity of those sources is a challenging aspect when multiple taxonomies have to be interlinked. In this paper we introduce the ACROSS system to support the alignment of independently created Web taxonomies. Each taxonomy is shaped by its unique culture, which is threefold: categorization criteria of the taxonomy, language, and socioeconomic background. For mapping categories between dierent taxonomies, ACROSS harnesses instance-level features as well as distant supervision from an intermediate source like multiple Wikipedia editions. ACROSS includes a reasoning step, which is based on combinatorial optimization. In order to reduce the run time of the reasoning procedure without sacricing quality, we study two models of user involvement. Our experiments with heterogeneous taxonomies for dierent domains demonstrate the viability of our approach and improvement over state-of-the-art baselines.

show abstract

Behavioral Intentions and Cognitive-Affective Effects of Exposure to YouTube Advertisements among College Students

Mahmoud

Abdelbaki

2019

المجلة العلمیة لبحوث العلاقات العامة و الإعلان

View full text Add to dashboard Cite

This study attempted to investigate the exposure to YouTube ads among Egyptian college students, their attitudes towards these ads, behavioral intentions to watch them and the effects of this exposure and to examine the relationships among these variables as well. The current study was theoretically guided by the theory of reasoned action (TRA) and cognitive-affective behavioral model (CAB) through a questionnaire administered to a purposive sample of 390 college students, who watch YouTube videos, from Cairo University, Egypt from February to May 2019.

show abstract

Multi-Cultural Interlinking of Web Taxonomies with ACROSS

Cited by 3 publications

References 24 publications

Uncovering Hidden Semantics of Set Information in Knowledge Bases

Uncovering Hidden Semantics of Set Information in Knowledge Bases

Multi-Cultural Interlinking of Web Taxonomies with ACROSS

Behavioral Intentions and Cognitive-Affective Effects of Exposure to YouTube Advertisements among College Students

Contact Info

Product

Resources

About