File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A neural knowledge graph evaluator: Combining structural and semantic evidence of knowledge graphs for predicting supportive knowledge in scientific QA

TitleA neural knowledge graph evaluator: Combining structural and semantic evidence of knowledge graphs for predicting supportive knowledge in scientific QA
Authors
KeywordsGraph neural networks
Knowledge graph
Network analysis
Scientific question answering
Text entailment analysis
Issue Date2020
PublisherElsevier Ltd. The Journal's web site is located at http://www.elsevier.com/locate/infoproman
Citation
Information Processing & Management, 2020, v. 57 n. 6, p. article no. 102309 How to Cite?
AbstractEffectively detecting supportive knowledge of answers is a fundamental step towards automated question answering. While pre-trained semantic vectors for texts have enabled semantic computation for background-answer pairs, they are limited in representing structured knowledge relevant for question answering. Recent studies have shown interests in enrolling structured knowledge graphs for text processing, however, their focus was more on semantics than on graph structure. This study, by contrast, takes a special interest in exploring the structural patterns of knowledge graphs. Inspired by human cognitive processes, we propose novel methods of feature extraction for capturing the local and global structural information of knowledge graphs. These features not only exhibit good indicative power, but can also facilitate text analysis with explainable meanings. Moreover, aiming to better combine structural and semantic evidence for prediction, we propose a Neural Knowledge Graph Evaluator (NKGE) which showed superior performance over existing methods. Our contributions include a novel set of interpretable structural features and the effective NKGE for compatibility evaluation between knowledge graphs. The methods of feature extraction and the structural patterns indicated by the features may also provide insights for related studies in computational modeling and processing of knowledge.
Persistent Identifierhttp://hdl.handle.net/10722/293699
ISSN
2019 Impact Factor: 4.787
2015 SCImago Journal Rankings: 0.897

 

DC FieldValueLanguage
dc.contributor.authorQIAO, C-
dc.contributor.authorHu, X-
dc.date.accessioned2020-11-23T08:20:32Z-
dc.date.available2020-11-23T08:20:32Z-
dc.date.issued2020-
dc.identifier.citationInformation Processing & Management, 2020, v. 57 n. 6, p. article no. 102309-
dc.identifier.issn0306-4573-
dc.identifier.urihttp://hdl.handle.net/10722/293699-
dc.description.abstractEffectively detecting supportive knowledge of answers is a fundamental step towards automated question answering. While pre-trained semantic vectors for texts have enabled semantic computation for background-answer pairs, they are limited in representing structured knowledge relevant for question answering. Recent studies have shown interests in enrolling structured knowledge graphs for text processing, however, their focus was more on semantics than on graph structure. This study, by contrast, takes a special interest in exploring the structural patterns of knowledge graphs. Inspired by human cognitive processes, we propose novel methods of feature extraction for capturing the local and global structural information of knowledge graphs. These features not only exhibit good indicative power, but can also facilitate text analysis with explainable meanings. Moreover, aiming to better combine structural and semantic evidence for prediction, we propose a Neural Knowledge Graph Evaluator (NKGE) which showed superior performance over existing methods. Our contributions include a novel set of interpretable structural features and the effective NKGE for compatibility evaluation between knowledge graphs. The methods of feature extraction and the structural patterns indicated by the features may also provide insights for related studies in computational modeling and processing of knowledge.-
dc.languageeng-
dc.publisherElsevier Ltd. The Journal's web site is located at http://www.elsevier.com/locate/infoproman-
dc.relation.ispartofInformation Processing & Management-
dc.subjectGraph neural networks-
dc.subjectKnowledge graph-
dc.subjectNetwork analysis-
dc.subjectScientific question answering-
dc.subjectText entailment analysis-
dc.titleA neural knowledge graph evaluator: Combining structural and semantic evidence of knowledge graphs for predicting supportive knowledge in scientific QA-
dc.typeArticle-
dc.identifier.emailHu, X: xiaoxhu@hku.hk-
dc.identifier.authorityHu, X=rp01711-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.ipm.2020.102309-
dc.identifier.scopuseid_2-s2.0-85085269123-
dc.identifier.hkuros318976-
dc.identifier.volume57-
dc.identifier.issue6-
dc.identifier.spagearticle no. 102309-
dc.identifier.epagearticle no. 102309-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats