Harvesting Knowledge from Social Networks: Extracting Typed Relationships Among Entities
Knowledge bases like DBpedia, Yago or Google’s Knowledge Graph contain huge amounts of ontological knowledge harvested from (semi-)structured, curated data sources, such as relational databases or XML and HTML documents. Yet, the Web is full of knowledge that is not curated and/or structured and, hence, not easily indexed, for example social data. Most work so far in this context has been dedicated to the extraction of entities, i.e., people, things or concepts. This paper describes our work toward the extraction of relationships among entities. The objective is reconstructing a typed graph of entities and relationships to represent the knowledge contained in social data, without the need for a-priori domain knowledge. The experiments with real datasets show promising performance across a variety of domains.
KeywordsSocial networks Relationship extraction Domain graph
- 1.Banko, M., Cafarella, M.J., Soderland, S., Broadhead, M., Etzioni, O.: Open information extraction from the web. In: IJCAI 2007, pp. 2670–2676 (2007)Google Scholar
- 2.Bird, S., Klein, E., Loper, E.: Natural Language Processing with Python. O’Reilly Media Inc., Sebastopol (2009)Google Scholar
- 3.Brambilla, M., Ceri, S., Daniel, F., Della Valle, E.: On the quest for changing knowledge. In: 2016 Proceedings of the International Workshop on Data-Driven Innovation on the Web, Co-located with Web Science, pp. 3:1–3:5 (2016)Google Scholar
- 4.Brambilla, M., Ceri, S., Della Valle, E., Volonterio, R., Acero Salazar, F.: Extracting emerging knowledge from social media. In: WWW 2017 (2017, in print)Google Scholar
- 5.Poon, H., Domingos, P.: Unsupervised ontology induction from text. In: ACL 2010, pp. 296–305 (2010)Google Scholar