• Publications
  • Influence
Learning Bilingual Lexicons from Monolingual Corpora
TLDR
We present a method for learning bilingual translation lexicons from monolingual corpora. Expand
  • 328
  • 45
  • PDF
Exploring Content Models for Multi-Document Summarization
TLDR
We present an exploration of generative probabilistic models for multi-document summarization. Expand
  • 364
  • 36
  • PDF
Prototype-Driven Learning for Sequence Models
We investigate prototype-driven learning for primarily unsupervised sequence modeling. Prior knowledge is specified declaratively, by providing a few canonical examples of each target annotationExpand
  • 215
  • 23
  • PDF
Joint Learning Improves Semantic Role Labeling
TLDR
We propose a discriminative log-linear joint model for semantic role labeling, which incorporates more global features and achieves superior performance in comparison to state-of-the art models. Expand
  • 202
  • 20
  • PDF
Structured Relation Discovery using Generative Models
TLDR
We propose a series of generative probabilistic models, broadly similar to topic models, each which generates a corpus of observed triples of entity mention pairs and the surface syntactic dependency path between them. Expand
  • 129
  • 16
  • PDF
Simple Coreference Resolution with Rich Syntactic and Semantic Features
TLDR
We present a simple approach which completely modularizes these three aspects. Expand
  • 201
  • 15
  • PDF
A Global Joint Model for Semantic Role Labeling
TLDR
We present a model for semantic role labeling that effectively captures the linguistic intuition that a semantic argument frame is a joint structure, with strong dependencies among the arguments. Expand
  • 154
  • 13
  • PDF
Unsupervised Coreference Resolution in a Nonparametric Bayesian Model
TLDR
We present an unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric structure within each document. Expand
  • 161
  • 12
  • PDF
Event Discovery in Social Media Feeds
TLDR
We present a novel method for record extraction from social streams such as Twitter. Expand
  • 192
  • 11
  • PDF
Coreference Resolution in a Modular, Entity-Centered Model
TLDR
We present a generative, model-based approach to coreference resolution in which each of these factors is modularly encapsulated and learned in a primarily unsu-pervised manner, resulting in the best results to date on the complete end-to-end coreference task. Expand
  • 169
  • 9
  • PDF