First workshop on NLP for Positive Impact

This workshop was postponed, please check out our 2021 website:


The growing prevalence of language-oriented AI systems has created opportunities for NLP and other AI technologies to have a major positive social impact. Much existing work on NLP for social good focuses on detecting or preventing harm, such as classifying hate speech or identifying signs of depression. However, NLP research also has the potential for positive proactive applications, such as increasing user well-being or fostering constructive conversations.

This workshop aims to promote NLP research that will positively impact society, specifically focusing on proactive and responsible methods. We will encourage submissions from areas including (but not limited to):

  • Positive conversation generation: models of conversation generation that promote constructive interactions or promote alternate perspectives; analyses of conversations with successful positive outcomes

  • Online prosocial behavior: models for positive rephrasing of online content; analyses of implied or stated altruism, empathy, or other prosocial behavior online

  • Well being: NLP techniques to improve the well-being of users, through (therapeutic) interaction or collaborative rewriting

  • Positive information sharing: natural language generation (NLG) of alternate perspectives to articles; contextual generation for (ambiguous) statements; mitigation of filter bubbles through generative methods

  • Interdisciplinary perspectives: perspectives and analyses from other fields (e.g., social sciences, philosophy) on the potential positive impacts of NLP techniques; cases studies of successful NLP applications

  • Other NLP for social good: e.g., NLP for disaster relief, models for helping users with cognitive or mental disabilities, etc.

Part of the workshop will promote investigation in two more focused challenges: (1) generating constructive and empathetic conversation, and (2) fostering compassion and perspective-taking in online platforms. The organizers have been collecting data for these challenges and will release the full data before the first call for papers.


Yejin Choi

University of Washington/Allen Institute for Artificial Intelligence

Jianfeng Gao

Microsoft Research

Yulia Tsvetkov

Carnegie Mellon University

Jason Weston

Facebook AI Research

Organizing Committee

  • Maarten Sap, University of Washington

  • Anjalie Field, Carnegie Mellon University

  • Michel Galley, Microsoft Research

  • Hannah Rashkin, University of Washington

  • Lianhui Karen Qin, University of Washington

  • Bill Dolan, Microsoft Research

Steering Committee

  • Yejin Choi, University of Washington / Allen Institute for Artificial Intelligence

  • Jianfeng Gao, Microsoft Research

  • Dan Jurafsky, Stanford University

  • Yulia Tsvetkov, Carnegie Mellon University

  • Jason Weston, Facebook AI Research