Alexander M. Rush

Assistant Professor.
Harvard School of Engineering and Applied Sciences. [srush@seas.harvard.edu] [cv]

My research group studies data-driven, probabilistic systems for natural language processing and generation. We are interested in empirically accurate methods that, when possible, are rooted in data and guided by efficient inference. Our recent work has focused on the intersection of deep learning and structured prediction, with an application focus on text generation and document-level understanding. We are also naturally system builders, and aim always to make our research replicable and hackable with open-source code.

Current Research Projects

  • Interpretable and controllable natural language generation for data-to-text summary
  • Deep generative models (e.g. VAEs) for probabilistic text processing and understanding.
  • Hardware for speech, translation, and dialogue with the Architecture and Hardware Group.
  • Visualization understanding of recurrent neural networks in collaboration with VCG and IBM.

Publications

Code

Conferences

  • Senior program chair for ICLR 2019 in New Orleans.
  • Area chair for NIPS 2019.
  • Tutorial on deep generative models for text at EMNLP 2018. (with Sam Wiseman and Yoon Kim)

Contact

Sasha Rush in person
srush at seas.harvard.edu by email
Maxwell-Dworkin 217 at work
Office Hours wed. 2:30-4 and by appointment

Students

If you are at Harvard and interested in NLP/ML, come take one of our courses: (CS181, CS182, CS187, CS281, CS287). We also hold a weekly reading group where we discuss new research and invite local speakers.

If you are interested in a applying for a Ph.D or postdoc, please email srush@seas.harvard.edu or stop by office hours Wed. 2:30-4 in MD 217.

Funding

Our group has been generously supported through research grants and gifts from the following industrial institutions: