Regina Barzilay

Style Transfer from Non-Parallel Text by Cross-Alignment

2017 · arXiv (Cornell University)

This paper focuses on style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and sentiment modification. The key challenge is to separate …

Learning Stable Classifiers by Transferring Unstable Features

2021 · arXiv (Cornell University)

While unbiased machine learning models are essential for many applications, bias is a human-defined concept that can vary across tasks. Given only input-label pairs, algorithms may lack sufficient information to distinguish stable (causal) features from …

Consistent Accelerated Inference via Confident Adaptive Transformers

2021 · arXiv (Cornell University)

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase efficiency, but can come …

InfoShape: Task-Based Neural Data Shaping via Mutual Information

2022 · arXiv (Cornell University)

The use of mutual information as a tool in private data sharing has remained an open challenge due to the difficulty of its estimation in practice. In this paper, we propose InfoShape, a task-based encoder …

Dirichlet Flow Matching with Applications to DNA Sequence Design

2024 · PubMed

Discrete diffusion or flow models could enable faster and more controllable sequence generation than autoregressive models. We show that na\"ive linear flow matching on the simplex is insufficient toward this goal since it suffers from …

Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing

2019

Tal Schuster, Ori Ram, Regina Barzilay, Amir Globerson. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.