@ ESWC 2020
Entity Summarization in Knowledge Graphs: Algorithms, Evaluation, and Applications
The concise representation format and graph nature of knowledge graphs have resulted in creating many novel Web applications and enhancing existing ones. However, in a knowledge graph, dozens or hundreds of facts describing an entity could exceed the capacity of a typical user interface and overload users with excessive amounts of information. This has motivated fruitful research on entity summarization---automated generation of compact summaries for entities to satisfy users' information needs efficiently and effectively. Over the recent years, researchers have contributed to this problem by proposing approaches ranging from pure ranking and mining techniques to machine and deep learning techniques. The state of the art has continuously improved and at the same time made it harder for the community and new comers to the problem to keep up with the recent and old contributions in the space. Moreover, even though knowledge graphs are becoming popular among academia and industry, there is no effort to date to educate and discuss on recent trends and basic building blocks of this problem domain. This tutorial specifically aims to fill this gap.
0:00--0:20 Introduction to knowledge graphs and entity summarization
0:20--1:00 Generic technical features for entity summarization
1:00--1:15 Specific technical features for entity summarization
1:15--1:30 Q & A
1:30--2:00 Frameworks for feature combination and representative algorithms
2:00--2:20 Evaluation methods and results
2:35--2:45 Conclusion and future directions
2:45--3:00 Q & A
Gong Cheng is an associate professor at the National Key Laboratory for Novel Software Technology, Nanjing University, China. His research interests include semantic search, data summarization, and question answering. He has published at WWW, ISWC, ESWC, AAAI, IJCAI, WSDM, CIKM, EMNLP and in TWEB, TKDE, JoWS, etc. He co-chaired the posters and demos track of ISWC 2019 and the tutorial track of JIST 2016. He was a co-organizer of many workshops including EYRE 2018--2019 co-located with CIKM, and SumPre 2015--2016 co-located with ESWC. He served as a PC member in a variety of conferences and workshops such as WWW, ISWC, ESWC, and JIST.
Kalpa Gunaratna is a senior research engineer at Samsung Research America, USA. He is interested in entity and data summarization, knowledge graphs, and applications of information retrieval and machine learning techniques for entity related data. His current research efforts at Samsung are centered around entities described in knowledge graphs and their efficient search and retrieval techniques on particular device platforms. He has published peer-reviewed papers on topics relevant to this tutorial at top-tier venues such as WWW, AAAI, and IJCAI and served as a PC member in WWW and ISWC. He was a co-organizer of EYRE 2018--2019 and SumPre 2015--2016.
Evgeny Kharlamov is a Research Scientist at the Bosch Centre for Artificial Intelligence and an Associate Professor at the University of Oslo. He does AI-centered research with the focus on how knowledge (semantics) and reasoning can enhance access and analyses of (big industrial) data. His work is motivated by and applied to the context of Industry 4.0, Knowledge Graphs, and Semantic Web. His work led to 120+ publications at conferences and journals including tier-1 VLDB, SIGMOD, CIKM, WWW, AAAI, TODS, ISWC. He was a sponsorship chair at ISWC’20, gave keynote talks at JIST’19 and KESW’13, got the best in-use paper award at ISWC’17, the best demo at ISWC’15, co-organized several workshops, and served as a PC member in a variety of venues.