Abdulkarim Kushk
ABSTRACT
Entity summarization is the task of generating a general-purpose abridged description of Knowledge Graph entities. It became a valuable task and attracted a lot of attention due to the explosion in the size of semantic datasets. While most existing methods are unsupervised and do not use deep learning, in this short research paper we present ESDL, a simple yet effective supervised deep learning model. In this model, we exploit textual semantics for encoding RDF triples. As a supervised model, it uses frequency scores programmatically extracted from human-generated summaries as labels for training. Experimental results on a public benchmark dataset show that our model achieved comparable F1 scores to the state-of-the-art model DeepLENS [1] and outperformed all other models with statistical significance. Furthermore, our model has a straightforward structure and less computational complexity, resulting in ESDL comparing favorably in terms of efficiency. Experiments show that ESDL is 40% faster than DeepLENS.
- Q. Liu, G. Cheng, and Y. Qu, "DeepLENS: Deep Learning for Entity Summarization," arXiv preprint arXiv:2003.03736, 2020.Google Scholar
- T. Berners-Lee, J. Hendler, and O. Lassila, "The semantic web," Scientific american, vol. 284, no. 5, pp. 34-43, 2001.Google ScholarCross Ref
- D. Sullivan. "A Reintroduction to our Knowledge Graph and Knowledge Panels." https://blog.google/products/search/about-knowledge-graph-and-knowledge-panels/ (accessed April 30, 2021).Google Scholar
- Q. Liu, G. Cheng, K. Gunaratna, and Y. Qu, "Entity summarization: State of the art and future challenges," arXiv preprint arXiv:1910.08252, 2019.Google Scholar
- Y. Li and L. Zhao, "A Common Property and Special Property Entity Summarization Approach Based on Statistical Distribution⋆," Director, vol. 4, no. 6, p. 8, 2016.Google Scholar
- A. G. Nuzzolese, V. Presutti, A. Gangemi, S. Peroni, and P. Ciancarini, "Aemoo: Linked data exploration based on knowledge patterns," Semantic Web, vol. 8, no. 1, pp. 87-112, 2017.Google ScholarDigital Library
- J. Waitelonis and H. Sack, "Towards exploratory video search using linked data," Multimedia Tools and Applications, vol. 59, no. 2, pp. 645-672, 2012.Google ScholarDigital Library
- K. Gunaratna, K. Thirunarayan, and A. Sheth, "FACES: diversity-aware entity summarization using incremental hierarchical conceptual clustering," in Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.Google Scholar
- K. Gunaratna, K. Thirunarayan, A. Sheth, and G. Cheng, "Gleaning types for literals in rdf triples with application to entity summarization," in European Semantic Web Conference, 2016: Springer, pp. 85-100.Google Scholar
- F. Hasibi, K. Balog, and S. E. Bratsberg, "Dynamic factual summaries for entity cards," in Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017, pp. 773-782.Google Scholar
- E.-k. Kim and K.-S. Choi, "Entity Summarization Based on Entity Grouping in Multilingual Projected Entity Space," IEICE TRANSACTIONS on Information and Systems, vol. 100, no. 9, pp. 2138-2146, 2017.Google ScholarCross Ref
- K. Gunaratna, A. H. Yazdavar, K. Thirunarayan, A. Sheth, and G. Cheng, "Relatedness-based multi-entity summarization," in IJCAI: proceedings of the conference, 2017, vol. 2017: NIH Public Access, p. 1060.Google Scholar
- G. Cheng, T. Tran, and Y. Qu, "Relin: relatedness and informativeness-based centrality for entity summarization," in International Semantic Web Conference, 2011: Springer, pp. 114-129.Google Scholar
- A. Thalhammer, I. Toma, A. Roa-Valverde, and D. Fensel, "Leveraging usage data for linked data movie entity summarization," arXiv preprint arXiv:1204.2718, 2012.Google Scholar
- J. Yan, Y. Wang, M. Gao, and A. Zhou, "Context-aware entity summarization," in International Conference on Web-Age Information Management, 2016: Springer, pp. 517-529.Google Scholar
- H. Kroll, D. Nagel, and W.-T. Balke, "BAFREC: Balancing Frequency and Rarity for Entity Characterization in Open Linked Data," 2018.Google Scholar
- A. Tonon, M. Catasta, R. Prokofyev, G. Demartini, K. Aberer, and P. Cudré-Mauroux, "Contextualized ranking of entity types based on knowledge graphs," Journal of Web Semantics, vol. 37, pp. 170-183, 2016.Google ScholarDigital Library
- M. Sydow, M. Pikuła, and R. Schenkel, "The notion of diversity in graphical entity summarisation on semantic knowledge graphs," Journal of Intelligent Information Systems, vol. 41, no. 2, pp. 109-149, 2013.Google ScholarDigital Library
- D. Wei, S. Gao, Y. Liu, Z. Liu, and L. Hang, "MPSUM: entity summarization with predicate-based matching," arXiv preprint arXiv:2005.11992, 2020.Google Scholar
- A. Thalhammer, N. Lasierra, and A. Rettinger, "Linksum: using link analysis to summarize entity data," in International Conference on Web Engineering, 2016: Springer, pp. 244-261.Google Scholar
- A. Thalhammer and A. Rettinger, "Browsing dbpedia entities with summaries," in European Semantic Web Conference, 2014: Springer, pp. 511-515.Google Scholar
- D. Wei and Y. Liu, "ESA: entity summarization with attention," arXiv preprint arXiv:1905.10625, 2019.Google Scholar
- Q. Liu, G. Cheng, K. Gunaratna, and Y. Qu, "ESBM: an entity summarization benchmark," in European Semantic Web Conference, 2020: Springer, pp. 548-564.Google Scholar
- D. Xu, L. Zheng, and Y. Qu, "CD at ENSEC 2016: Generating Characteristic and Diverse Entity Summaries," in SumPre@ ESWC, 2016.Google Scholar
- E. Kim and K.-S. Choi, "Entity summarization based on formal concept analysis," in 1st International Workshop on Entity REtrieval, EYRE, 2018.Google Scholar
Index Terms
- ESDL: Entity Summarization with Deep Learning
Recommendations
Arabic named entity recognition via deep co-learning
Named entity recognition (NER) is an important natural language processing (NLP) task with many applications. We tackle the problem of Arabic NER using deep learning based on Arabic word embeddings that capture syntactic and semantic relationships ...
Entity Linking for Biomedical Literature
DTMBIO '14: Proceedings of the ACM 8th International Workshop on Data and Text Mining in BioinformaticsThe Entity Linking (EL) task links entity mentions from an unstructured document to entities in a knowledge base. Although this problem is well-studied in news and social media, this problem has not received much attention in the life science domain. ...
Deep Active-Self Learning Applied to Named Entity Recognition
Intelligent SystemsAbstractDeep learning models have been the state-of-the-art for a variety of challenging tasks in natural language processing, but to achieve good results they often require big labeled datasets. Deep active learning algorithms were designed to reduce the ...
Comments