• Publications
  • Influence
Improving Machine Learning Approaches to Coreference Resolution
TLDR
We present a noun phrase coreference system that extends the work of Soon et al. (2001) and, to our knowledge, produces the best results to date on the MUC-6 andMUC-7 coreference resolution data sets. Expand
  • 729
  • 82
  • PDF
Automatic Keyphrase Extraction: A Survey of the State of the Art
TLDR
We present a survey of the state of the art in automatic keyphrase extraction, examining the major sources of errors made by existing systems and discussing the challenges ahead. Expand
  • 357
  • 41
  • PDF
Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge
TLDR
We examine the task of resolving complex cases of definite pronouns, specifically those for which traditional linguistic constraints on coreference (e.g., Binding Constraints, gender and number agreement) are not useful. Expand
  • 123
  • 33
  • PDF
Identifying Anaphoric and Non-Anaphoric Noun Phrases to Improve Coreference Resolution
TLDR
We present a supervised learning approach to identification of anaphoric and non-anaphoric noun phrases and show how such information can be incorporated into a coreference resolution system. Expand
  • 174
  • 31
  • PDF
Conundrums in Unsupervised Keyphrase Extraction: Making Sense of the State-of-the-Art
TLDR
State-of-the-art approaches for unsupervised keyphrase extraction are typically evaluated on a single dataset with a single parameter setting, and how sensitive they are to changes in parameter settings. Expand
  • 166
  • 22
  • PDF
Examining the Role of Linguistic Knowledge Sources in the Automatic Identification and Classification of Reviews
TLDR
This paper examines two problems in document-level sentiment analysis: (1) determining whether a given document is a review or not and (2) classifying the polarity of a review as positive or negative. Expand
  • 272
  • 20
  • PDF
Supervised Noun Phrase Coreference Research: The First Fifteen Years
TLDR
The research focus of computational coreference resolution has exhibited a shift from heuristic approaches to machine learning approaches in the past decade. Expand
  • 260
  • 18
  • PDF
Stance Classification of Ideological Debates: Data, Models, Features, and Constraints
TLDR
We examine how the performance of a learning-based stance classification system varies with the amount and quality of the training data, the complexity of the underlying model, the richness of the feature set, and the application of extra-linguistic constraints. Expand
  • 155
  • 17
  • PDF
Why are You Taking this Stance? Identifying and Classifying Reasons in Ideological Debates
TLDR
We propose to address post-level RC by means of sentence-level reason classification (RC) in ideological debates. Expand
  • 130
  • 12
  • PDF
Supervised Models for Coreference Resolution
TLDR
We propose a cluster-ranking approach to coreference resolution that combines the strengths of mention rankers and entitymention models and demonstrate its superior performance to competing approaches. Expand
  • 157
  • 12
  • PDF
...
1
2
3
4
5
...