• Publications
  • Influence
Word Representations: A Simple and General Method for Semi-Supervised Learning
TLDR
In this work, we compare different techniques for inducing word representations, evaluating them on the tasks of named entity recognition (NER) and chunking. Expand
  • 2,008
  • 170
  • PDF
Design Challenges and Misconceptions in Named Entity Recognition
TLDR
We analyze some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system that achieves 90.8 F1 score on the CoNLL-2003 NER shared task. Expand
  • 1,221
  • 131
  • PDF
Local and Global Algorithms for Disambiguation to Wikipedia
TLDR
We analyze approaches that utilize the Wikipedia link graph to arrive at coherent sets of disambiguations for a given document, and compare them to more traditional (local) approaches. Expand
  • 641
  • 115
  • PDF
Guiding Semi-Supervision with Constraint-Driven Learning
TLDR
This paper proposes a novel constraints-based learning protocol for guiding semi-supervised learning. Expand
  • 211
  • 33
  • PDF
Importance of Semantic Representation: Dataless Classification
TLDR
We introduce Dataless Classification, a learning protocol that uses world knowledge to induce classifiers without the need for any labeled data. Expand
  • 130
  • 13
  • PDF
Structured learning with constrained conditional models
TLDR
This paper presents Constrained Conditional Models (CCMs), a framework that augments linear models with declarative constraints in an expressive output space while maintaining modularity and tractability of training. Expand
  • 111
  • 11
  • PDF
Learning-based Multi-Sieve Co-reference Resolution with Knowledge
TLDR
We explore the interplay of knowledge and structure in co-reference resolution. Expand
  • 61
  • 6
  • PDF
Learning to Shift the Polarity of Words for Sentiment Classification
TLDR
We propose a machine learning based method of sentiment classification of sentences using word-level polarity. Expand
  • 90
  • 5
  • PDF
CUNY-UIUC-SRI TAC-KBP2011 Entity Linking System Description
TLDR
In this paper we describe a joint effort by the City University of New York (CUNY), University of Illinois at Urbana-Champaign (UIUC) and SRI International at participating in the mono-lingual entity linking task for the NIST Text Analysis Conference (TAC) Knowledge Base Population (KBP2011) track. Expand
  • 34
  • 4
  • PDF
Learning and Inference with Constraints
TLDR
We present Constraints Conditional Models (CCMs), a framework that augments probabilistic models with declarative constraints as a way to support decisions in an expressive output space while maintaining modularity and tractability of training. Expand
  • 77
  • 2
  • PDF