Many prediction tasks in NLP involve assigning values to mutually dependent variables. For example, when designing a model to automatically perform linguistic analysis of a sentence or a document (e.g., parsing, semantic role labeling, or discourse analysis), it is crucial to model the correlations between labels. Many other NLP tasks, such as machine translation, textual entailment, and information extraction, can be also modeled as structured prediction problems.

In order to tackle such problems, various structured prediction approaches have been proposed, and their effectiveness has been demonstrated. Studying structured prediction is interesting from both NLP and machine learning (ML) perspectives. From the NLP perspective, syntax and semantics of natural language are clearly structured and advances in this area will enable researchers to understand the linguistic structure of data. From the ML perspective, the large amount of available text data and complex linguistic structures bring challenges to the learning community. Designing expressive yet tractable models and studying efficient learning and inference algorithms become important issues.

This workshop follows the three previous successful editions in 2019, 2017 and 2016 on Structured Prediction for NLP, as well as the closely related ICML 17 Workshop on Deep Structured Prediction. It is very timely, as there has been a renewed interest in structured prediction among NLP researchers due to recent advances in methods using continuous representations, able to learn with task-level supervision, or modelling latent linguistic structure.

Topics will include, but are not limited to, the following:

  • Efficient learning and inference algorithms
  • Joint inference and learning approaches
  • Reinforcement learning and imitation learning for structured learning in NLP
  • Multi-task learning for structured output tasks
  • Latent structured variable models
  • Structured deep generative models
  • Neural graph learning approaches for NLP
  • Integer linear programming and other modeling techniques
  • Approximate inference for structured prediction
  • Structured training for non-linear models
  • Deep learning and neural network approaches for structured prediction
  • Structured prediction software
  • Structured prediction applications in NLP

We invite submissions of the following kinds:

  • Research papers
  • Position papers
  • Tutorial/overview papers

Invited Speakers

  • Isabelle Augenstein, University of Copenhagen
  • Jonathan Berant, Tel-Aviv University
  • Mark Johnson, Macquarie University
  • Alexander Rush, Cornell Tech
  • Sunita Sarawagi, IIT Bombay
  • Ivan Titov, University of Edinburgh


Program Committee

  • Sweta Agrawal, University of Maryland, USA
  • Naveen Arivazhagan, Google Research, USA
  • Yoav Artzi, Cornell University, USA
  • Wilker Aziz, University of Amsterdam, Netherlands
  • Colin Cherry, Google Research, Canada
  • Gonçalo Correia, Instituto de Telecomunicacoes, Portugal
  • George Foster, Google Research, Canada
  • Kevin Gimpel, TTI Chicago, USA
  • Parag Jain, University of Edinburgh, UK
  • Arzoo Katiyar, Cornell University, USA
  • Yoon Kim, MIT-IBM Watson AI Lab, USA
  • Parisa Kordjamshidi, Tulane University, USA
  • Chunchuan Lyu, University of Edinburgh, UK
  • Pranava Madhyastha, Imperial College London, UK
  • Zita Marinho, Sacoor Brothers, Portugal
  • Musie Meressa, Sapienza University of Rome, Italy
  • Sabrina J Mielke, Johns Hopkins University, USA
  • Toan Q Nguyen, University of Notre Dame, USA
  • Vlad Niculae, University of Amsterdam, Netherlands
  • Marek Rei, University of Cambridge, UK
  • Hiko Schamoni, Heidelberg University, Germany
  • Tianze Shi, Cornell University, USA
  • Vivek Srikumar, University of Utah, USA
  • Sean J Welleck, New York University, USA


We invite submissions of the following kinds:

  • Research papers
  • Position papers
  • Tutorial/overview papers

Long/short papers should consist of eight/four pages of content plus unlimited pages for bibliography. Submissions must be in PDF format following the EMNLP 2020 templates, anonymized for review. Papers can be submitted as non-archival, so that their content can be reused for other venues. Add “(NON-ARCHIVAL)” to the title of the submission. Non-archival papers will be linked from this webpage if their authors wish to. Previously published work can also be submitted as non-archival in the same way, with the additional requirement to state on the first page the original publication. Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well.

Papers can be dual-submitted to both SPNLP 2020 and EMNLP 2020 main conference which has its notification date of August 8, 2020 falling before our submission deadline. If submitted as archival and it is accepted in both EMNLP and SPNLP, you would need to withdraw from one of them. You can submitting normally and can make the archival decision after the EMNLP notification

Submission is electronic and is managed by the START conference management system at

Each submission will be reviewed by at least 2 program committee members.

Important Dates

  • Submission deadline: August 20, 2020
  • Notification of acceptance: September 29, 2020
  • Camera-ready papers due: October 10, 2020
  • Workshop date: November 20, 2020

Time is in GMT-12. Deadline is 11:59pm of the date indicated.