Andrew Drozdov

Graduate Student at UMass Amherst

I’m a PhD student in Computer Science at UMass Amherst and member of both UMass NLP and IESL. I work with Professors Andrew McCallum and Mohit Iyyer on developing neural methods for text processing. My research interests are in automatic structure discovery, instance-based learning, and text generation.

Previously, I’ve completed my Master’s in Computer Science at NYU where I worked with Professors Samuel Bowman and Kyunghyun Cho, and was a member of ML2 and CILVR. While at NYU I worked with reinforcement learning and deep syntactic models for natural language understanding.

I’ve also interned at Google Research on the AI Language Team and Brain Team, at IBM Research, and worked multiple years as a Software Engineer before starting graduate school.

selected publications

  1. Long Paper Poster
    Inducing and Using Alignments for Transition-based AMR Parsing
    Andrew Drozdov, Jiawei Zhou, Radu Florian, Andrew McCallum, Tahira Naseem, Yoon Kim, and Ramon Fernandez Astudillo
    In NAACL 2022
  2. Long Paper Poster
    Improved Latent Tree Induction with Distant Supervision via Span Constraints
    Zhiyang Xu, Andrew Drozdov, Jay Yoon Lee, Tim O’Gorman, Subendhu Rongali, Dylan Finkbeiner, Shilpa Suresh, Mohit Iyyer, and Andrew McCallum
    In EMNLP 2021
  3. Long Paper Poster
    Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders
    Andrew Drozdov, Subendhu Rongali, Yi-Pei Chen, Tim O’Gorman, Mohit Iyyer, and Andrew McCallum
    In EMNLP 2020
  4. Long Paper Oral
    The Impact of Preprint Servers in the Formation of Novel Ideas
    Swarup Satish, Zonghai Yao, Andrew Drozdov, and Boris Veytsman
    In EMNLP (Workshop on Scholarly Document Processing) 2020
  5. Short Paper Poster
    Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Auto-Encoders
    Andrew Drozdov, Patrick Verga, Yi-Pei Chen, Mohit Iyyer, and Andrew McCallum
    In EMNLP 2019
  6. Long Paper Oral
    Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders
    Andrew Drozdov, Patrick Verga, Mohit Yadav, Mohit Iyyer, and Andrew McCallum
    In NAACL 2019
  7. Journal Oral
    Do latent tree learning models identify meaningful structure in sentences?
    Adina Williams, Andrew Drozdov, and Samuel R. Bowman
    TACL 2018
  8. Long Paper Poster
    Emergent Communication in a Multi-Modal, Multi-Step Referential Game
    Katrina Evtimova, Andrew Drozdov, Douwe Kiela, and Kyunghyun Cho
    In ICLR 2018
  9. Ext. Abstract Poster
    The Coadaptation Problem when Learning How and What to Compose
    Andrew Drozdov, and Samuel R. Bowman
    In ACL (Workshop on Representation Learning for NLP) 2017