Share This Author
Word Representations: A Simple and General Method for Semi-Supervised Learning
This work evaluates Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeds of words on both NER and chunking, and finds that each of the three word representations improves the accuracy of these baselines.
Design Challenges and Misconceptions in Named Entity Recognition
Some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system are analyzed, and several solutions to these challenges are developed.
Local and Global Algorithms for Disambiguation to Wikipedia
This work analyzes approaches that utilize information from Wikipedia link structure to arrive at coherent sets of disambiguations for a given document, and compares them to more traditional (local) approaches.
Guiding Semi-Supervision with Constraint-Driven Learning
The experimental results presented in the information extraction domain demonstrate that applying constraints helps the model to generate better feedback during learning, and hence the framework allows for high performance learning with significantly less training data than was possible before on these tasks.
Importance of Semantic Representation: Dataless Classification
This paper introduces Dataless Classification, a learning protocol that uses world knowledge to induce classifiers without the need for any labeled data, and proposes a model for dataless classification and shows that the label name alone is often sufficient to induceclassifiers.
Structured learning with constrained conditional models
This paper presents Constrained Conditional Models (CCMs), a framework that augments linear models with declarative constraints as a way to support decisions in an expressive output space while maintaining modularity and tractability of training and proposes CoDL, a constraint-driven learning algorithm, which makes use of constraints to guide semi-supervised learning.
Learning-based Multi-Sieve Co-reference Resolution with Knowledge
This work uses a state-of-the-art system which cross-links expressions in free text to Wikipedia to inject knowledge, and deploys a learning-based multi-sieve approach and develops novel entity-based features.
Learning to Shift the Polarity of Words for Sentiment Classification
This work proposes a machine learning based method of sentiment classification of sentences using word-level polarity and empirically shows that this method improves the performance of sentiment Classification of sentences especially when the authors have only small amount of training data.
Learning and Inference with Constraints
Constraints Conditional Models is presented, 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 and it is shown that declaratives constraints can be used to take advantage of unlabeled data when training the probabilism model.
CUNY-UIUC-SRI TAC-KBP2011 Entity Linking System Description
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…