Maxwell Dworkin 208
33 Oxford Street
Cambridge, MA 02138
I’m a postdoc at Harvard SEAS, where I work on natural language processing, focusing on language representations in neural networks. I’m affiliated with the Mind, Brain, Behavior initiative and work mainly with Stuart Shieber. I’m also affiliated with the NLP group and the CCNLab at Harvard.
I maintain an active collaboration with the Spoken Language Systems group at MIT CSAIL, where I completed my PhD under the supervision of James Glass. My PhD thesis analyzed internal langauge representations in deep learning models, with particular applications to machine translation and speech recognition.
Before coming to MIT I worked as a software engineer in IntuView while pursuing a Master’s in Arabic Studies at Tel Aviv University with a thesis on the Arabic dialect of Jisir izZarga. My undergrauate degree was in Mathematics and Arabic Studies, also at Tel Aviv University.
I’ll be joining the Technion Computer Science Department as a faculty member in Fall 2020.
|May 13, 2019||Two papers accepted at ACL 2019.|
|Jan 16, 2019||Co-organizing BlackboxNLP 2019.|
|Dec 21, 2018||Paper accepted at ICLR 2019.|
|Apr 26, 2018||Defended my PhD thesis.|
|Jan 30, 2018||Paper accepted for oral presentation at ICLR 2018.|
|Sep 4, 2017||Paper accepted at NIPS 2017.|
|Aug 16, 2017||Speaking at the Boston NLP Meetup.|
|May 29, 2017||Speaking at DSEU.|
|Mar 30, 2017||Two papers accepted at ACL 2017.|
|Feb 6, 2017||Paper accepted at ICLR 2017.|
- Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference, ACL 2019
- Synthetic and Natural Noise Both Break Neural Machine Translation", ICLR 2018
- Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems, NIPS 2017
- What do Neural Machine Translation Models Learn about Morphology?, ACL 2017
- Arabic Diacritization with Recurrent Neural Networks, EMNLP 2015
- Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment, TACL 2014