TL;DR: A system for extracting typed dependency parses of English sentences from phrase structure parses that captures inherent relations occurring in corpus texts that can be critical in real-world applications is described.
Abstract: This paper describes a system for extracting typed dependency parses of English sentences from phrase structure parses. In order to capture inherent relations occurring in corpus texts that can be critical in real-world applications, many NP relations are included in the set of grammatical relations used. We provide a comparison of our system with Minipar and the Link parser. The typed dependency extraction facility described here is integrated in the Stanford Parser, available for download.
TL;DR: The dependency model of media effects is presented as a theoretical alternative in which the nature of the tripartite audience-media-society relationship is assumed to most directly determine many of the effects that the media have on people and society as discussed by the authors.
Abstract: It is suggested that one of the reasons that there is such a lack of clarity as to whether the media have effects is that researchers have proceeded from the wrong theoretical conceptualizations to study the wrong questions. The dependency model of media effects is presented as a theoretical alternative in which the nature of the tripartite audience-media-society relationship is assumed to most directly determine many of the effects that the media have on people and society. The present paper focuses upon audience dependency on media information resources as a key interactive condition for alteration of audience beliefs, behavior, or feelings as a result of mass communicated in formation. Audience dependency is said to be high in societies in which the media serve many central information functions and in periods of rapid social change or pervasive social conflict. The dependency model is further elaborated and illustrated by examination of several cognitive, affective, and behavioral effects which may be...
TL;DR: Experiments on extracting top-level relations from the ACE (Automated Content Extraction) newspaper corpus show that the new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels.
Abstract: We present a novel approach to relation extraction, based on the observation that the information required to assert a relationship between two named entities in the same sentence is typically captured by the shortest path between the two entities in the dependency graph. Experiments on extracting top-level relations from the ACE (Automated Content Extraction) newspaper corpus show that the new shortest path dependency kernel outperforms a recent approach based on dependency tree kernels.