{"type":"ScholarlyArticle","title":"Neural Entity Summarization with Joint Encoding and Weak Supervision","authors":[{"name":"Junyou Li","slug":"junyou-li","given":"Junyou","family":"Li","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Gong Cheng","slug":"gong-cheng","given":"Gong","family":"Cheng","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Qingxia Liu","slug":"qingxia-liu","given":"Qingxia","family":"Liu","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Wen Zhang","slug":"wen-zhang","given":"Wen","family":"Zhang","affiliation":"College of Computer Science and Technology , Zhejiang University , China; Bosch Center for Artificial Intelligence , Robert Bosch GmbH , Germany"},{"name":"Evgeny Kharlamov","slug":"evgeny-kharlamov","given":"Evgeny","family":"Kharlamov","affiliation":"Bosch Center for Artificial Intelligence , Robert Bosch GmbH , Germany; Department of Informatics , University of Oslo , Norway"},{"name":"Kalpa Gunaratna","slug":"kalpa-gunaratna","given":"Kalpa","family":"Gunaratna","affiliation":"Samsung Research America , Mountain View CA , USA"},{"name":"Huajun Chen","slug":"huajun-chen","given":"Huajun","family":"Chen","affiliation":"College of Computer Science and Technology , Zhejiang University , China"}],"abstract":"In a large-scale knowledge graph (KG), an entity is often described by a large number of triple-structured facts. Many applications require abridged versions of entity descriptions, called entity summaries. Existing solutions to entity summarization are mainly unsupervised. In this paper, we present a supervised approach NEST that is based on our novel neural model to jointly encode graph structure and text in KGs and generate high-quality diversified summaries. Since it is costly to obtain manually labeled summaries for training, our supervision is weak as we train with programmatically labeled data which may contain noise but is free of manual work. Evaluation results show that our approach significantly outperforms the state of the art on two public benchmarks.","doi":"10.24963/ijcai.2020/228","url":"https://ijcai.org/proceedings/2020/228","pdf":"https://ijcai.org/proceedings/2020/0228.pdf","markdown":"https://ijcai.org/proceedings/2020/228.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/228","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Knowledge Representation and Reasoning","track":"Main track","number":228,"pages":{"first":1644,"last":1650},"keywords":["Machine Learning: Deep Learning","Machine Learning: Learning Preferences or Rankings","Knowledge Representation and Reasoning: Semantic Web"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24218/file_24218.m3u8","length_sec":287,"provider":"hls"}],"references":[{"position":1,"raw":"[Bojanowski et al., 2017] Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. Enriching word vec- tors with subword information. Trans. Assoc. Comput. Linguist., 5:135-146, 2017.","title":"Enriching word vectors with subword information","authors":"Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov","year":"2017","venue":"Trans. Assoc. Comput. Linguist","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bordes et al., 2013] Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In NIPS, pages 2787-2795, 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai et al., 2018] HongYun Cai, Vincent W. Zheng, and Kevin Chen-Chuan Chang. A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Trans. Knowl. Data Eng., 30(9):1616-1637, 2018.","title":"A comprehensive survey of graph embedding: Problems, techniques, and applications","authors":"Hongyun Cai, Vincent W Zheng, Kevin Chen, -Chuan Chang","year":"2018","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng et al., 2011] Gong Cheng, Thanh Tran, and Yuzhong Qu. RELIN: relatedness and informativeness-based cen- trality for entity summarization. In ISWC, Part I, pages 114-129, 2011.","title":"RELIN: relatedness and informativeness-based centrality for entity summarization","authors":"Cheng","year":"2011","venue":"ISWC, Part I","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2015a] Gong Cheng, Danyun Xu, and Yuzhong Qu. C3D+P: A summarization method for interactive entity resolution. J. Web Semant., 35:203-213, 2015.","title":"C3D+P: A summarization method for interactive entity resolution","authors":"Cheng","year":"2015","venue":"J. Web Semant","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheng et al., 2015b] Gong Cheng, Danyun Xu, and Yuzhong Qu. Summarizing entity descriptions for effec- tive and efficient human-centered entity linking. In WWW, pages 184-194, 2015.","title":"Summarizing entity descriptions for effective and efficient human-centered entity linking","authors":"Cheng","year":"2015","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cochez et al., 2017] Michael Cochez, Petar Ristoski, Si- mone Paolo Ponzetto, and Heiko Paulheim. Global RDF vector space embeddings. In ISWC, Part I, pages 190-207, 2017.","title":"Global RDF vector space embeddings","authors":"Michael Cochez, Petar Ristoski, Simone Paolo Ponzetto, Heiko Paulheim","year":"2017","venue":"ISWC, Part I","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cui et al., 2019] Peng Cui, Xiao Wang, Jian Pei, and Wenwu Zhu. A survey on network embedding. IEEE Trans. Knowl. Data Eng., 31(5):833-852, 2019.","title":"A survey on network embedding","authors":"Peng Cui, Xiao Wang, Jian Pei, Wenwu Zhu","year":"2019","venue":"IEEE Trans. Knowl. Data Eng","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gesese et al., 2019] Genet Asefa Gesese, Russa Biswas, Mehwish Alam, and Harald Sack. A survey on knowl- edge graph embeddings with literals: Which model links better literal-ly? CoRR, abs/1910.12507:1-24, 2019.","title":"A survey on knowledge graph embeddings with literals: Which model links better literal-ly?","authors":"Gesese","year":"2019","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gunaratna et al., 2015] Kalpa Gunaratna, Krishnaprasad Thirunarayan, and Amit P. Sheth. FACES: diversity-aware entity summarization using incremental hierarchical con- ceptual clustering. In AAAI, pages 116-122, 2015.","title":"FACES: diversity-aware entity summarization using incremental hierarchical conceptual clustering","authors":"Kalpa Gunaratna, Krishnaprasad Thirunarayan, Amit P Sheth","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gunaratna et al., 2016] Kalpa Gunaratna, Krishnaprasad Thirunarayan, Amit P. Sheth, and Gong Cheng. Gleaning types for literals in RDF triples with application to entity summarization. In ESWC, pages 85-100, 2016.","title":"Gleaning types for literals in RDF triples with application to entity summarization","authors":"Kalpa Gunaratna, Krishnaprasad Thirunarayan, P Amit, Gong Sheth, Cheng","year":"2016","venue":"ESWC","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gunaratna et al., 2017] Kalpa Gunaratna, Amir Hossein Yazdavar, Krishnaprasad Thirunarayan, Amit P. Sheth, and Gong Cheng. Relatedness-based multi-entity summariza- tion. In IJCAI, pages 1060-1066, 2017.","title":"Relatedness-based multi-entity summarization","authors":"Kalpa Gunaratna, Krishnaprasad Amir Hossein Yazdavar, Thirunarayan, P Amit, Gong Sheth, Cheng","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/147"},{"position":13,"raw":"[Hachey et al., 2017] Ben Hachey, Will Radford, and An- drew Chisholm. Learning to generate one-sentence biogra- phies from Wikidata. In EACL, pages 633-642, 2017.","title":"and Andrew Chisholm. Learning to generate one-sentence biographies from Wikidata","authors":"Hachey","year":"2017","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hasibi et al., 2017] Faegheh Hasibi, Krisztian Balog, and Svein Erik Bratsberg. Dynamic factual summaries for en- tity cards. In SIGIR, pages 773-782, 2017.","title":"Dynamic factual summaries for entity cards","authors":"Hasibi","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lebret et al., 2016] Rémi Lebret, David Grangier, and Michael Auli. Neural text generation from structured data with application to the biography domain. In EMNLP, pages 1203-1213, 2016.","title":"Neural text generation from structured data with application to the biography domain","authors":"Lebret","year":"2016","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu and Lapata, 2019] Yang Liu and Mirella Lapata. Text summarization with pretrained encoders. In EMNLP- IJCNLP, pages 3728-3738, 2019.","title":"Text summarization with pretrained encoders","authors":"Yang Liu, Mirella Lapata","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2019] Qingxia Liu, Gong Cheng, Kalpa Gu- naratna, and Yuzhong Qu. Entity summarization: State of the art and future challenges. CoRR, abs/1910.08252:1- 40, 2019.","title":"Entity summarization: State of the art and future challenges","authors":"Liu","year":"2019","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2020] Qingxia Liu, Gong Cheng, Kalpa Gu- naratna, and Yuzhong Qu. ESBM: an entity summariza- tion benchmark. In ESWC, pages 1-16, 2020.","title":"ESBM: an entity summarization benchmark","authors":"Liu","year":"2020","venue":"ESWC","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ristoski et al., 2019] Petar Ristoski, Jessica Rosati, Tom- maso Di Noia, Renato De Leone, and Heiko Paulheim. RDF2Vec: RDF graph embeddings and their applications. Semant. Web, 10(4):721-752, 2019.","title":"RDF2Vec: RDF graph embeddings and their applications","authors":"Petar Ristoski, Jessica Rosati, Tommaso Di Noia, Renato De Leone, Heiko Paulheim","year":"2019","venue":"Semant. Web","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sun et al., 2019] Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. RotatE: knowledge graph embedding by relational rotation in complex space. In ICLR, pages 1-18, 2019.","title":"RotatE: knowledge graph embedding by relational rotation in complex space","authors":"Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, Jian Tang","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sydow et al., 2013] Marcin Sydow, Mariusz Pikula, and Ralf Schenkel. The notion of diversity in graphical entity summarisation on semantic knowledge graphs. J. Intell. Inf. Syst., 41(2):109-149, 2013.","title":"The notion of diversity in graphical entity summarisation on semantic knowledge graphs","authors":"Marcin Sydow, Mariusz Pikula, Ralf Schenkel","year":"2013","venue":"J. Intell. Inf. Syst","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Thalhammer et al., 2016] Andreas Thalhammer, Nelia Lasierra, and Achim Rettinger. LinkSUM: using link analysis to summarize entity data. In ICWE, pages 244-261, 2016.","title":"LinkSUM: using link analysis to summarize entity data","authors":"Andreas Thalhammer, Nelia Lasierra, Achim Rettinger","year":"2016","venue":"ICWE","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vougiouklis et al., 2018] Pavlos Vougiouklis, Hady ElSa- har, Lucie-Aimée Kaffee, Christophe Gravier, Frédérique Laforest, Jonathon Hare, and Elena Simperl. Neural Wikipedian: Generating textual summaries from knowl- edge base triples. J. Web Semant., 52-53:1-15, 2018.","title":"Neural Wikipedian: Generating textual summaries from knowledge base triples","authors":"Pavlos Vougiouklis, Hady Elsahar, Lucie-Aimée Kaffee, Christophe Gravier, Frédérique Laforest, Jonathon Hare, Elena Simperl","year":"2018","venue":"J. Web Semant","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xie et al., 2016] Ruobing Xie, Zhiyuan Liu, Jia Jia, Huanbo Luan, and Maosong Sun. Representation learning of knowledge graphs with entity descriptions. In AAAI, pages 2659-2665, 2016.","title":"Representation learning of knowledge graphs with entity descriptions","authors":"Ruobing Xie, Zhiyuan Liu, Jia Jia, Huanbo Luan, Maosong Sun","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xu et al., 2016] Danyun Xu, Liang Zheng, and Yuzhong Qu. CD at ENSEC 2016: Generating characteristic and diverse entity summaries. In SumPre, pages 1-3, 2016.","title":"CD at ENSEC 2016: Generating characteristic and diverse entity summaries","authors":"Danyun Xu, Liang Zheng, Yuzhong Qu","year":"2016","venue":"SumPre","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xu et al., 2017] Jiacheng Xu, Xipeng Qiu, Kan Chen, and Xuanjing Huang. Knowledge graph representation with jointly structural and textual encoding. In IJCAI, pages 1318-1324, 2017.","title":"Knowledge graph representation with jointly structural and textual encoding","authors":"Xu","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/183"},{"position":27,"raw":"[Zhang et al., 2012] Lanbo Zhang, Yi Zhang, and Yunfei Chen. Summarizing highly structured documents for ef- fective search interaction. In SIGIR, pages 145-154, 2012.","title":"Summarizing highly structured documents for effective search interaction","authors":"Lanbo Zhang, Yi Zhang, Yunfei Chen","year":"2012","venue":"SIGIR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}