论文信息 - DeepLENS: Deep Learning for Entity Summarization

DeepLENS: Deep Learning for Entity Summarization

Entity summarization has been a prominent task over knowledge graphs. While existing methods are mainly unsupervised, we present DeepLENS, a simple yet effective deep learning model where we exploit textual semantics for encoding triples and we score each candidate triple based on its interdependence on other triples. DeepLENS significantly outperformed existing methods on a public benchmark.

Gong Cheng | Qingxia Liu | Yuzhong Qu

[2] Yuzhong Qu,et al. CD at ENSEC 2016: Generating Characteristic and Diverse Entity Summaries , 2016, SumPre@ESWC.

[3] Yaxin Liu,et al. ESA: Entity Summarization with Attention , 2019, ArXiv.

[5] Gong Cheng,et al. ESBM: An Entity Summarization BenchMark , 2020, ESWC.

[6] Amit P. Sheth,et al. Gleaning Types for Literals in RDF Triples with Application to Entity Summarization , 2016, ESWC.

[7] Tomas Mikolov,et al. Enriching Word Vectors with Subword Information , 2016, TACL.

[8] Gong Cheng,et al. Entity Summarization: State of the Art and Future Challenges , 2019, ArXiv.

[9] Yuzhong Qu,et al. RELIN: Relatedness and Informativeness-Based Centrality for Entity Summarization , 2011, International Semantic Web Conference.

[10] Amit P. Sheth,et al. FACES: Diversity-Aware Entity Summarization Using Incremental Hierarchical Conceptual Clustering , 2015, AAAI.

[11] Marcin Sydow,et al. The notion of diversity in graphical entity summarisation on semantic knowledge graphs , 2013, Journal of Intelligent Information Systems.

[12] Zhibing Liu,et al. MPSUM: Entity Summarization with Predicate-based Matching , 2020, ArXiv.

[13] Nelia Lasierra,et al. LinkSUM: Using Link Analysis to Summarize Entity Data , 2016, ICWE.