Alexander RushAssociate Professor.
CS+Cornell Tech (NYC), Cornell NLP
Researcher. Hugging Face
My research aims to build NLP systems that are safe, fast, and controllable. We are interested primarily in tasks that involve text generation such as machine translation, document summarization, and data-to-text generation. Methodologically, we study data-driven probabilistic methods that combine deep-learning based models with probabilistic controls.
I am also interested in open-source NLP and deep learning, and develop projects to make deep learning systems safer, more clear, and easier to use. I work part-time at Hugging Face and like to release various software projects to support NLP and DL research.
Current Research Areas
- Interpretable and controllable natural language generation for data-to-text summary.
- Deep generative models for probabilistic text processing and understanding.
- Efficient algorithms and hardware for speech, translation, and dialogue.
- Visual tools for understanding of neural language models.
My group's work has been recognized with an NSF CAREER Award and a Sloan Fellowship. We have won paper awards at conferences for NLP, Hardware, and Visualization, as well as awards for best demonstrations for open-source software.
A selection of papers from the last five years that represent my research interests and style.
Transformers: State-of-the-art Natural Language Processing
Thomas Wolf et al.
EMNLP Demos 2020
Compound Probabilistic Context-Free Grammars for Grammar Induction
Yoon Kim, Chris Dyer, Alexander M. Rush.
Learning Neural Templates for Text Generation
Sam Wiseman, Stuart M. Shieber, Alexander Rush.
LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
Hendrik Strobelt, Sebastian Gehrmann, Hanspeter Pfister, and Alexander M. Rush.
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, Alexander M. Rush.
ACL Demo 2017
Sequence-Level Knowledge Distillation
Yoon Kim and Alexander M. Rush.
Character-Aware Neural Language Models
Yoon Kim, Yacine Jernite, David Sontag, and Alexander M. Rush.
A Neural Attention Model for Abstractive Sentence Summarization
Alexander M. Rush, Sumit Chopra, and Jason Weston.