Tim Vieira

About

I develop machine learning algorithms for tough problems—tending toward applications in natural language processing and programming languages. I am currently a postdoctoral researcher working with Ryan Cotterell. I did my PhD with Jason Eisner at Johns Hopkins University. I've also worked with Andrew McCallum on Rexa and Factorie; Dan Roth on Textual Entailment. I did my undergraduate degree at the University of Illinois Urbana-Champaign.

Fun

When I'm not in front of a whiteboard or computer, I'm probably climbing things, walking around on my hands, or hanging out with Hanna Wallach and our adorable dog, Maia.

Blog

Technical blog: Graduate Descent. Twitter: @xtimv.

Publications

• Automating the Analysis and Improvement of Dynamic Programming Algorithms with Applications to Natural Language Processing Tim Vieira PhD Dissertation 2023
  video slides code
• Efficient Semiring-Weighted Earley Parsing Andreas Opedal, Ran Zmigrod, Tim Vieira, Ryan Cotterell, Jason Eisner ACL 2023
  arXiv code video poster
• A Formal Perspective on Byte-Pair Encoding Vilém Zouhar, Clara Meister, Juan Gastaldi, Li Du, Tim Vieira, Mrinmaya Sachan, Ryan Cotterell ACL 2023
  arXiv code video poster
• Algorithms for Weighted Pushdown Automata Alexandra Butoi, Brian DuSell, Tim Vieira, Ryan Cotterell, David Chiang EMNLP 2022
  arXiv code
• Algorithms for Weighted Finite-State Automata with Failure Arcs Anej Svete, Benjamin Dayan, Ryan Cotterell, Tim Vieira, Jason Eisner EMNLP 2022
  arXiv code
• On the Intersection of Context-Free and Regular Languages Clemente Pasti, Andreas Opedal, Tiago Pimentel, Tim Vieira, Jason Eisner, Ryan Cotterell EACL 2023
  arXiv code video
• Exact Paired-Permutation Testing for Structured Test Statistics Ran Zmigrod, Tim Vieira, Ryan Cotterell NAACL 2022
  arXiv code video
• Searching for More Efficient Dynamic Programs Tim Vieira, Ryan Cotterell, Jason Eisner Findings of EMNLP 2021
  slides video arXiv
• Conditional Poisson Stochastic Beam Search Clara Meister, Afra Amini, Tim Vieira, Ryan Cotterell EMNLP 2021
  code arXiv video
• Efficient Sampling of Dependency Structures Ran Zmigrod, Tim Vieira, Ryan Cotterell EMNLP 2021
  code arXiv video
• Efficient Computation of Expectations under Spanning Tree Distributions Ran Zmigrod,* Tim Vieira,* Ryan Cotterell TACL 2021
  code arXiv video
• On Finding the K-best Non-projective Dependency Trees Ran Zmigrod, Tim Vieira, Ryan Cotterell ACL 2021
  code arXiv video
• Higher-order Derivatives of Weighted Finite-state Machines Ran Zmigrod, Tim Vieira, Ryan Cotterell ACL 2021
  code arXiv video
• If Beam Search is the Answer, What was the Question? Clara Meister, Tim Vieira, Ryan Cotterell EMNLP 2020
  code arXiv video Honorable mention paper 🏆
• Please Mind the Root: Decoding Arborescences for Dependency Parsing Ran Zmigrod, Tim Vieira, Ryan Cotterell EMNLP 2020
  code arXiv video
• Best-First Beam Search Clara Meister, Tim Vieira, Ryan Cotterell TACL 2020
  code arXiv slides
• Evaluation of Logic Programs with Built-Ins and Aggregation: A Calculus for Bag Relations Matthew Francis-Landau, Tim Vieira, Jason Eisner WRLA 2020
  code
• The Universal Decompositional Semantics Dataset and Decomp Toolkit Aaron Steven White, Elias Stengel-Eskin, Siddharth Vashishtha, Venkata Subrahmanyan Govindarajan, Dee Ann Reisinger, Tim Vieira, Keisuke Sakaguchi, Sheng Zhang, Francis Ferraro, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme LREC 2020
  arxiv project page
• Forward-Backward with Failure Arcs: Faster Inference for Variable-Order Conditional Random Fields Tim Vieira,* Ryan Cotterell,* and Jason Eisner arXiv 2018 (preprint)
  code
• Dyna: Toward a Self-Optimizing Declarative Language for Machine Learning Applications Tim Vieira, Matthew Francis-Landau, Nathaniel Wesley Filardo, Farzad Khorasani, Jason Eisner MAPL 2017
  slides video
• Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing Tim Vieira and Jason Eisner TACL 2017 (oral presentation at ACL 2017)
  code slides video
• Speed-Accuracy Tradeoffs in Tagging with Variable-Order CRFs and Structured Sparsity Tim Vieira,* Ryan Cotterell,* and Jason Eisner EMNLP 2016
  code poster
• Universal Decompositional Semantics on Universal Dependencies Aaron Steven White, Drew Reisinger, Keisuke Sakaguchi, Tim Vieira, Sheng Zhang, Rachel Rudinger, Kyle Rawlins, Benjamin Van Durme EMNLP 2016
  website code
• A Joint Model of Orthography and Morphological Segmentation Ryan Cotterell, Tim Vieira, Hinrich Schütze NAACL 2016
  
  code data slides Best short paper runner up! 🏆
• Reasoning about Quantities in Natural Language Subhro Roy, Tim Vieira, Dan Roth TACL 2015
  code
• Grammarless Parsing for Joint Inference Jason Naradowsky, Tim Vieira, David A. Smith COLING 2012
  code
• Relation Alignment for Textual Entailment Recognition M. Sammons, V. Vydiswaran, T. Vieira, N. Johri, M. Chang, D. Goldwasser, V. Srikumar, G. Kundu, Y. Tu, K. Small, J. Rule, Q. Do, D. Roth TAC 2009