Most of the knowledge available on the Web is encoded in natural language texts or Web documents aimed primarily at human consumption. A promising approach to have programmatic access to such knowledge uses information extraction techniques that aim to extract machine readable structures from free texts, from which it is possible to retrieve entities and categories. These entities can potentially be linked to each other, creating de facto a global knowledge graph of linked entities.
The WoLE2012 workshop envisions the Web as a Web of Linked Entities (WoLE), which transparently connects the World Wide Web (WWW) and the Giant Global Graph (GGG) using methods from Information Retrieval (IR) and Natural Language Processing (NLP). The focus of this workshop is to bring together the Information Retrieval, Semantic Web and NLP communities. The primary goal is to strengthen research techniques that provide access to textual information published on the Web to further improve the adoption of Semantic Web technology.
- Fabian M. Suchanek (Max Planck Institute for Informatics)
- Giuseppe Rizzo (EURECOM)
- Pablo Mendes (Freie Universität Berlin)
- Eric Charton (CRIM)
- Sebastian Hellmann (AKSW)
- Aditya Kalyanpur (IBM)