Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

A Discriminative Graph-Based Parser for the Abstract Meaning Representation

• Jeffrey Flanigan, Sam Thomson, Jaime G. Carbonell, Chris Dyer, Noah A. Smith
• ACL
• 2014

Abstract Meaning Representation (AMR) is a semantic formalism for which a growing set of annotated examples is available. We introduce the first approach to parse sentences into this representation,… (More)

Toward Abstractive Summarization Using Semantic Representations

• Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman M. Sadeh, Noah A. Smith
• HLT-NAACL
• 2015

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… (More)

Neural Motifs: Scene Graph Parsing with Global Context

• Rowan Zellers, Mark Yatskar, Sam Thomson, Yejin Choi
• IEEE/CVF Conference on Computer Vision and…
• 2018

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… (More)

Frame-Semantic Role Labeling with Heterogeneous Annotations

• Meghana Kshirsagar, Sam Thomson, Nathan Schneider, Jaime G. Carbonell, Noah A. Smith, Chris Dyer
• ACL
• 2015

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… (More)

Deep Multitask Learning for Semantic Dependency Parsing

• Hao Peng, Sam Thomson, Noah A. Smith
• ACL
• 2017

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… (More)

Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold

• Swabha Swayamdipta, Sam Thomson, Chris Dyer, Noah A. Smith
• ArXiv
• 2017

I Variant of a semi-Markov conditional random field (Sarawagi and Kohen, 2004) I Span representations are computed using bidirectional RNNs. I Provide a generalization of BIO tagging schemes. I… (More)

Clostridium difficile-associated disease acquired in the cardiothoracic intensive care unit.

• Saif A Musa, Carl Moran, +4 authors Tony Manibur Rahman
• Journal of cardiothoracic and vascular anesthesia
• 2011

OBJECTIVES To determine the prevalence, severity, and outcome associated with Clostridium difficile-associated disease (CDAD) acquired while in the cardiothoracic intensive care unit (CTICU). … (More)

Clostridium difficile infection and inflammatory bowel disease.

• Saif A Musa, Sam Thomson, Matthew Cowan, Tony Manibur Rahman
• Scandinavian journal of gastroenterology
• 2010

The importance of Clostridium difficile (C. difficile) infection amongst patients with inflammatory bowel disease (IBD) is increasingly being recognized. Recent studies have demonstrated a concerning… (More)

Chronic liver disease--an increasing problem: a study of hospital admission and mortality rates in England, 1979-2005, with particular reference to alcoholic liver disease.

• Sam Thomson, Susan Westlake, +4 authors J Y Kang
• Alcohol and alcoholism
• 2008

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… (More)

SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines

• Roy Schwartz, Sam Thomson, Noah A. Smith
• ArXiv
• 2018

Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model… (More)

• ‹
• 1
• 2
• 3
• ›