• Publications
  • Influence
LIBLINEAR: A Library for Large Linear Classification
LIBLINEAR is an open source library for large-scale linear classification. It supports logistic regression and linear support vector machines. We provide easy-to-use command-line tools and libraryExpand
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
This work empirically demonstrates that its algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks. Expand
A dual coordinate descent method for large-scale linear SVM
A novel dual coordinate descent method for linear SVM with L1-and L2-loss functions that reaches an ε-accurate solution in O(log(1/ε)) iterations is presented. Expand
VisualBERT: A Simple and Performant Baseline for Vision and Language
Analysis demonstrates that VisualBERT can ground elements of language to image regions without any explicit supervision and is even sensitive to syntactic relationships, tracking, for example, associations between verbs and image regions corresponding to their arguments. Expand
Generating Natural Language Adversarial Examples
A black-box population-based optimization algorithm is used to generate semantically and syntactically similar adversarial examples that fool well-trained sentiment analysis and textual entailment models with success rates of 97% and 70%, respectively. Expand
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods
A data-augmentation approach is demonstrated that, in combination with existing word-embedding debiasing techniques, removes the bias demonstrated by rule-based, feature-rich, and neural coreference systems in WinoBias without significantly affecting their performance on existing coreference benchmark datasets. Expand
Learning Gender-Neutral Word Embeddings
A novel training procedure for learning gender-neutral word embeddings that preserves gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence is proposed. Expand
A Comparison of Optimization Methods and Software for Large-scale L1-regularized Linear Classification
Extensive comparisons indicate that carefully implemented coordinate descent methods are very suitable for training large document data. Expand
Learning to Search Better than Your Teacher
A new learning to search algorithm, LOLS, is provided, which does well relative to the reference policy, but additionally guarantees low regret compared to deviations from the learned policy: a local-optimality guarantee. Expand
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
This work proposes to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference that results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification. Expand