- Publications
- Influence
IEEE/CVF Conference on Computer Vision and…
We investigate the problem of producing structured graph representations of visual scenes. Our work analyzes the role of motifs: regularly appearing substructures in scene graphs. We present new… Expand
Abstract Meaning Representation (AMR) is a semantic formalism for which a grow- ing set of annotated examples is avail- able. We introduce the first approach to parse sentences into this representa-… Expand
We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed… Expand
We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a… Expand
We consider the task of identifying and labeling the semantic arguments of a predicate that evokes a FrameNet frame. This task is challenging because there are only a few thousand fully annotated… Expand
We present a new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates. Built using an extension to the segmental RNN that emphasizes recall, our basic system… Expand
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a… Expand
OBJECTIVES
To determine the prevalence, severity, and outcome associated with Clostridium difficile-associated disease (CDAD) acquired while in the cardiothoracic intensive care unit (CTICU).
… Expand
AIMS
To determine time trends in hospital admissions for chronic liver disease in England between 1989/1990 and 2002/2003, mortality rates in England and Wales between 1979 and 2005, and the… Expand
We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle… Expand