Applications closed

Robust Deep Learning for Natural Language Processing request for proposals


While neural networks have achieved the state-of-the-art results on various natural language processing (NLP) tasks, their robustness to changes in the input distribution and their ability to transfer to related tasks are one of the biggest open challenges. Modern NLP systems interact with text from heterogeneous sources with distinct distributions while the underlying linguistic regularities may be shared across tasks. This presents several interrelated challenges:

  • From an application perspective, these models need to produce a robust output at test time given diverse inputs, even if such input distributions have never been observed at training time. For instance, content on the internet can be characterized by informal language with a long tail of variations in terms of lexical choice, spelling, style/genre, emerging vocabularies (slang, memes, etc.) and other linguistic phenomena.
  • From the machine learning perspective, we need theoretical and empirical understanding of the intrinsic behaviors of neural networks used in NLP tasks both at training and inference time. For example, how to derive formal verification of a model’s robustness for a specific task? What training objectives and optimization methods can improve robustness to adversarial input at prediction time? Given neural models are trained on large amounts of data from heterogenous sources, how is model quality affected by noise/bias in training data? At inference time, what are unbiased and robust evaluation protocols to assess whether the model has improved linguistic generalization capability?

Less robust models can lead to low-quality outputs while being exposed to natural noise, being susceptible to adversarial inputs, or catastrophic failures in the extreme case. We invite the academic community to propose novel and robust methods to address the above challenges.

Award Recipients

Massachusetts Institute of Technology

Regina Barzilay

Carnegie Mellon University

Zachary Lipton

University of Massachusetts Amherst

Brendan O'Connor

Stanford University

Christopher Potts

Applications Are Currently CLosed

Application Timeline

Notifications will be sent by email to selected applicants by July 28, 2019.

Launch Date

April 5, 2019


May 31, 2019

Winners Announced

July 28, 2019

Areas of Interest

Research topics should be relevant to understanding and improving the robustness of neural NLP systems (Machine Translation, Question Answering, Representation Learning), including but not limited to:

  • Novel modeling approaches and learning methods to improve neural network’s generalization capability towards diverse linguistic phenomena, such as lexical choice variation, colloquial language and style/genre variation, orthographical variation, code-switching, etc. Progress can be shown either on individual language (language family) or cross-lingually
  • Empirical and theoretical results on robustness challenges facing state-of-the-art neural models for various NLP tasks (e.g. the GLUE benchmark), such as representation learning, classification, machine translation, question answering and natural language inference
  • Efficient approaches to improve and evaluate adaptation to new domains/tasks with input and output distributions different from those seen during training, which demonstrate improvements on transfer in terms of quality and robustness over specific techniques such as domain adaptation, mixed domain training, few-shot learning, meta learning and other weak supervision from large amounts of unlabeled data
  • Understanding and improving adversarial robustness. This includes defining what adversarial examples mean for different NLP tasks, methods for generating these examples, formal verification of model robustness, as well as techniques to defend against adversarial examples (both natural adversarial input and intentional adversarial attack)


Proposals should include

  • A summary of the project (1-2 pages) explaining the area of focus, a description of techniques, any relevant prior work and a timeline with milestones and expected outcomes
  • A draft budget description (1 page) including an approximate cost of the award and explanation of how funds would be spent. Budgets should include travel costs to a workshop hosted at Facebook in Menlo Park, CA. Proposals will be accepted for projects up to $80k and lasting up to 12 months
  • Curriculum Vitae for all project participants
  • Organization details, i.e. tax information and administrative contact details


  • Awards must comply with applicable US and international laws, regulations and policies.
  • Applicants must be current full-time faculty at an accredited academic institution that awards research degrees to PhD students.
  • Applicants must be the Principal Investigator on any resulting award.
  • Applicants may submit one proposal per solicitation.
  • Organizations must be a nonprofit or non-governmental organization with recognized legal status in their respective country (equal to 501(c)(3) status under the United States Internal Revenue Code).

Additional Information

Recipients will be invited to attend a workshop at Menlo Park, CA in August 2020.

Terms & Conditions

  • By submitting a proposal, you are authorizing Facebook to evaluate the proposal for a potential award, and you agree to the terms herein.
  • You agree that Facebook will not be required to treat any part of the proposal as confidential or protected by copyright.
  • You agree and acknowledge that personal data submitted with the proposal, including name, mailing address, phone number, and email address of you and other named researchers in the proposal may be collected, processed, stored and otherwise used by Facebook for the purposes of administering the website and evaluating the contents of the proposal.
  • You acknowledge that neither party is obligated to enter into any business transaction as a result of the proposal submission, Facebook is under no obligation to review or consider the proposal, and neither party acquires any intellectual property rights as a result of submitting the proposal.
  • Any feedback you provide to Facebook in the proposal regarding its products or services will not be treated as confidential or protected by copyright, and Facebook is free to use such feedback on an unrestricted basis with no compensation to you.