Semantic role labeling for structured information extraction
Diana Trandabăţ · 2011
This paper presents a semantic role labeling system acting as the backbone of an application that monitors the contexts and relations in which a specified entity appears in written texts. Using semantic role analysis, we are able to answer questions such as: "What roles do entities play in different contexts?" or "When, why, where or how an event takes place?" Thus, by starting with an input entity, the system extracts the first 200 web pages found on a Google search for the particular entity, extracts relevant paragraphs that contain the entity, and then performs semantic role labeling on the extracted paragraphs. The main goal is to identify the role this entity plays, as well as the roles played by words frequently co-occurring with the input entity.