Event Extraction and Synthesis
Papers from the AAAI Workshop
Naveen Ashish, Doug Appelt, Dayne Freitag, and Dmitry Zelenko, Cochairs
The focus of this workshop is on the extraction of events from textual or other modalities of information. While extraction of entities and relations from text and unstructured data is by now a well-explored research area, extracting events from text or other forms of raw input poses new challenges. Events have on average greater structural complexity than entities or relations, and the problem of narrative uncertainty, expressly stated or implicit, is more in evidence. An example is the following sentence from a Voice of America news report: “The United Nations says Somali gunmen who hijacked a U.N.-chartered vessel carrying food aid for tsunami victims have released the ship after holding it for more than two months.” This sentence expresses multiple events—a focal event (the release of a hijacked ship), and several contextual events providing a temporal and semantic framework for it. Extracting event information of this complexity appears to call for ideas from multiple disciplines, such as machine learning, natural language understanding, knowledge representation, database systems, and linguistic theory related to language semantics.