Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Andrew Moore

Andrew Moore

Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification


Oct 16, 2020
Andrew Moore, Jeremy Barnes

Figure 1 for Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification
Figure 2 for Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification
Figure 3 for Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification
Figure 4 for Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification

  Access Paper or Ask Questions

FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms


Jun 28, 2019
Henry B. Moss, Andrew Moore, David S. Leslie, Paul Rayson

Figure 1 for FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms
Figure 2 for FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms
Figure 3 for FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms
Figure 4 for FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms
* ACL 2019. Code available at: https://github.com/apmoore1/fiesta 
  Access Paper or Ask Questions

Bringing replication and reproduction together with generalisability in NLP: Three reproduction studies for Target Dependent Sentiment Analysis


Aug 06, 2018
Andrew Moore, Paul Rayson

Figure 1 for Bringing replication and reproduction together with generalisability in NLP: Three reproduction studies for Target Dependent Sentiment Analysis
Figure 2 for Bringing replication and reproduction together with generalisability in NLP: Three reproduction studies for Target Dependent Sentiment Analysis
Figure 3 for Bringing replication and reproduction together with generalisability in NLP: Three reproduction studies for Target Dependent Sentiment Analysis
Figure 4 for Bringing replication and reproduction together with generalisability in NLP: Three reproduction studies for Target Dependent Sentiment Analysis
* COLING 2018. Code available at: https://github.com/apmoore1/Bella 
  Access Paper or Ask Questions

Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines


May 01, 2017
Andrew Moore, Paul Rayson

Figure 1 for Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines
Figure 2 for Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines
* 5 pages, to Appear in the Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval 2017), August 2017, Vancouver, BC 
  Access Paper or Ask Questions

The Anchors Hierachy: Using the triangle inequality to survive high dimensional data


Jan 16, 2013
Andrew Moore

Figure 1 for The Anchors Hierachy: Using the triangle inequality to survive high dimensional data
Figure 2 for The Anchors Hierachy: Using the triangle inequality to survive high dimensional data
Figure 3 for The Anchors Hierachy: Using the triangle inequality to survive high dimensional data
Figure 4 for The Anchors Hierachy: Using the triangle inequality to survive high dimensional data
* Appears in Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI2000) 
  Access Paper or Ask Questions

Mix-nets: Factored Mixtures of Gaussians in Bayesian Networks With Mixed Continuous And Discrete Variables


Jan 16, 2013
Scott Davies, Andrew Moore

Figure 1 for Mix-nets: Factored Mixtures of Gaussians in Bayesian Networks With Mixed Continuous And Discrete Variables
Figure 2 for Mix-nets: Factored Mixtures of Gaussians in Bayesian Networks With Mixed Continuous And Discrete Variables
* Appears in Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI2000) 
  Access Paper or Ask Questions

Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes


Dec 12, 2012
Andrew Moore, Jeff Schneider

Figure 1 for Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes
Figure 2 for Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes
Figure 3 for Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes
Figure 4 for Real-valued All-Dimensions search: Low-overhead rapid searching over subsets of attributes
* Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002) 
  Access Paper or Ask Questions

Interpolating Conditional Density Trees


Dec 12, 2012
Scott Davies, Andrew Moore

Figure 1 for Interpolating Conditional Density Trees
Figure 2 for Interpolating Conditional Density Trees
Figure 3 for Interpolating Conditional Density Trees
Figure 4 for Interpolating Conditional Density Trees
* Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002) 
  Access Paper or Ask Questions