• Publications
  • Influence
Message Understanding Conference- 6: A Brief History
TLDR
We have recently completed the sixth in a series of "Message Understanding Conferences" which are designed to promote and evaluate research in information extraction. Expand
  • 1,318
  • 110
  • PDF
The NomBank Project: An Interim Report
TLDR
This paper describes NomBank, a project that will provide argument structure for instances of common nouns in the Penn Treebank II corpus. Expand
  • 344
  • 56
  • PDF
Overview of the TAC 2010 Knowledge Base Population Track
TLDR
In this paper we give an overview of the Knowledge Base Population (KBP) track at TAC 2010. Expand
  • 491
  • 44
  • PDF
Joint Event Extraction via Recurrent Neural Networks
TLDR
We propose to do event extraction in a joint framework with bidirectional recurrent neural networks, thereby benefiting from the advantages of the two models as well as addressing issues inherent in the existing approaches. Expand
  • 218
  • 42
  • PDF
Discovering Relations among Named Entities from Large Corpora
TLDR
We propose an unsupervised method for relation discovery from large corpora. Expand
  • 429
  • 36
  • PDF
Relation Extraction: Perspective from Convolutional Neural Networks
TLDR
We introduce a convolutional neural network for relation extraction that automatically learns features from sentences and minimizes the dependence on external toolkits and resources. Expand
  • 321
  • 36
  • PDF
A Procedure for Quantitatively Comparing the Syntactic Coverage of English Grammars
TLDR
The problem of quantitatively comparing the performance of different broad-coverage grammars of English has to date resisted solution. Expand
  • 538
  • 35
  • PDF
Comlex Syntax: Building a Computational Lexicon
TLDR
We describe the design of Comlex Syntax, a computational lexicon providing detailed syntactic information for approximately 38,000 English headwords. Expand
  • 277
  • 29
  • PDF
A maximum entropy approach to named entity recognition
TLDR
This thesis describes a novel statistical named-entity (i.e. “proper name”) recognition system known as “MENE” (Maximum Entropy Named Entity). Expand
  • 485
  • 25
NOMLEX: a lexicon of nominalizations
TLDR
NOMLEX is a dictionary of English nominalizations being developed by the Proteus Project at New York University. Expand
  • 145
  • 24
  • PDF