Query-driven on-the-fly knowledge base construction

Abstract

Today's openly available knowledge bases, such as DBpedia, Yago, Wikidata or Freebase, capture billions of facts about the world's entities. However, even the largest among these (i) are still limited in up-to-date coverage of what happens in the real world, and (ii) miss out on many relevant predicates that precisely capture the wide variety of relationships among entities. To overcome both of these limitations, we propose a novel approach to build on-the-fly knowledge bases in a query-driven manner. Our system, called QKBfly, supports analysts and journalists as well as question answering on emerging topics, by dynamically acquiring relevant facts as timely and comprehensively as possible. QKBfly is based on a semantic-graph representation of sentences, by which we perform three key IE tasks, namely named-entity disambiguation, co-reference resolution and relation extraction, in a light-weight and integrated manner. In contrast to Open IE, our output is canonicalized. In contrast to traditional IE, we capture more predicates, including ternary and higher-arity ones. Our experiments demonstrate that QKBfly can build high-quality, on-the-fly knowledge bases that can readily be deployed, e.g., for the task of ad-hoc question answering. PVLDB Reference Format:

PNEL: Pointer Network Based End-To-End Entity Linking over Knowledge Graphs

“…It is not an end-to-end model but is the most recent work which presents elaborate evaluation on Wikidata based datasets, hence we include it in evaluations. We also include QKBFly [19] and TagME [7] in our evaluations because KB-Pearl includes results for these systems on a common dataset (LC-QuAD 2.0). QKBFly performs on-the-fly knowledge base construction for ad-hoc text.…”

Swat: A system for detecting salient Wikipedia entities in texts

“…The key idea underlying these approaches consists of identifying in the input text meaningful sequences of terms and link them to unambiguous entities drawn from a Knowledge Base (KB), such as Wikipedia, DBpedia, Freebase, Wikidata, YAGO, or BabelNet . Since these entities occur as nodes in a graph, new and more sophisticated methods have been designed to empower classic approaches and thus enabling a number of significant improvements among different domains, such as microblog enrichment and analysis, text classification and clustering, KB construction, and query understanding …”

“…The key idea underlying these approaches consists of identifying in the input text meaningful sequences of terms and link them to unambiguous entities drawn from a Knowledge Base (KB), such as Wikipedia, DBpedia (Bizer et al, 2009), Freebase (Bollacker et al, 2008), Wikidata (Vrandečić and Kr ötzsch, 2014, YAGO (Suchanek et al, 2007), or BabelNet (Navigli and Ponzetto, 2012). Since these entities occur as nodes in a graph, new and more sophisticated methods have been designed in order to empower classic approaches and thus enabling a number of significant improvements among different domains, such as microblog enrichment and analysis (Ferragina et al, 2015;Liu et al, 2013;Meij et al, 2012), text classification and clustering (Scaiella et al, 2012;Vitale et al, 2012), KB construction (Niu et al, 2012;Bovi et al, 2015;Nguyen et al, 2017) and query understanding (Blanco et al, 2015;Hasibi et al, 2017;Cornolti et al, 2018).…”

LearningToAdapt with word embeddings: Domain adaptation of Named Entity Recognition systems

“…The possibility to easily access and exploit these sophisticated NER systems through APIs or pre-trained models became fundamental for addressing tasks such as Data Integration [34,58], Question Answering [55,5,73], Privacy Protection [20,46] , and Knowledge Base Construction [56].…”