Andrew Drozdov

Research Scientist @ Databricks (starting soon)

PhD @ UMass Amherst CICS
Thesis: Unlocking Natural Language Generalization through Adaptive Retrieval-based Methods
Advisors: Andrew McCallum, Mohit Iyyer
TA: CS 685, CS 696DS
Organizer: Data Science Tea

MS @ NYU CS
Mentors: Samuel Bowman, Kyunghyun Cho

Previously at Google and IBM.

Say hello: adrozdov@cs.umass.edu

Research

I’m broadly interested in neural network-related topics including training, inference, in-context learning, knowledge distillation, and evaluation. Most of my work has been in natural language processing and information retrieval. I’m particularly excited about the emerging field of generative retrieval.

Publications

  1. Short Paper
    PaRaDe: Passage Ranking using Demonstrations with LLMs
    Andrew Drozdov, Honglei Zhuang, Zhuyun Dai, Zhen Qin, Razieh Rahimi, Xuanhui Wang, Dana Alon, Mohit Iyyer, Andrew McCallum, Donald Metzler, and Kai Hui
    In EMNLP (Findings) 2023
  2. Long Paper
    kNN-LM Does Not Improve Open-ended Text Generation
    Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella, Varun Manjunatha, and Mohit Iyyer
    In EMNLP 2023
  3. Long Paper Poster
    Compositional Semantic Parsing with Large Language Models
    Andrew Drozdov, Nathanael Schärli, Ekin Akyürek, Nathan Scales, Xinying Song, Xinyun Chen, Olivier Bousquet, and Denny Zhou
    In ICLR 2023
  4. Long Paper Findings
    You can’t pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM
    Andrew Drozdov, Shufan Wang, Razieh Rahimi, Andrew McCallum, Hamed Zamani, and Mohit Iyyer
    In EMNLP (Findings) 2022
  5. 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
  6. 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
  7. 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
  8. 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
  9. 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
  10. 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
  11. Journal Oral
    Do latent tree learning models identify meaningful structure in sentences?
    Adina Williams, Andrew Drozdov, and Samuel R. Bowman
    TACL 2018
  12. 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
  13. 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