First Workshop on Causal Inference & NLP

Panel Discussion

For our panel discussion, we have invited experts in NLP and causal inference to discuss their recent work at this intersection and vision for the future. We will discuss both estimating causal effects from text and using causality to better inform NLP prediction.

Panelists:

• Aron Culotta, Tulane, https://cs.tulane.edu/~aculotta/
• Amir Feder, Technion, https://amirfeder.github.io/
• Jacob Eisenstein, Google, https://jacobeisenstein.github.io/
• Dhanya Sridhar, University of Montreal, https://dsridhar91.github.io/
• Brandon Stewart, Princeton, https://scholar.princeton.edu/bstewart/home
• Justine Zhang, Stanford, https://tisjune.github.io/

Accepted Papers

Note: Accepted papers will be shared via live 10-minute presentations during the paper oral sessions. Attendees will have the opportunity to interact further with paper authors during the poster session.

Oral Session I

1. • Causal Augmentation for Causal Sentence Classification (virtual, poster)
   • Fiona Anting Tan, Devamanyu Hazarika, See-Kiong Ng, Soujanya Poria and Roger Zimmermann
2. • Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects (in-person, poster)
   • Katherine Keith, Douglas Rice and Brendan O’Connor
3. • Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US (in-person, poster, paper)
   • Zhijing Jin, Zeyu Peng, Tejas Vaidhya, Bernhard Schoelkopf and Rada Mihalcea
4. • Sensitivity Analysis for Causal Mediation through Text: an Application to Political Polarization (in-person, poster)
   • Graham Tierney and Alexander Volfovsky
5. • An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog (in-person, paper)
   • Xingyao Wang and David Jurgens
6. • ConceptData: The Challenges of Creating a Causal Benchmark for Explanation Methods in NLP (virtual, poster)
   • Eldar D. Abraham, Amir Feder and Roi Reichart

Oral Session II

1. • It’s quality and quantity: the effect of the amount of comments on online suicidal posts (in-person, poster)
   • Daniel M. Low, Kelly Zuromski, Daniel Kessler, Satrajit S. Ghosh, Matthew K. Nock and Walter Dempsey
2. • Media Slant is Contagious (virtual, paper)
   • Elliott Ash, Philine Widmer and Sergio Galletta
3. • Enhancing Model Robustness and Fairness with Causality: A Regularization Approach (virtual, poster)
   • Zhao Wang, Kai Shu and Aron Culotta
4. • What Makes a Scientific Paper be Accepted for Publication? (virtual)
   • Panagiotis Fytas, Georgios Rizos and Lucia Specia
5. • A Survey of Online Hate Speech through the Causal Lens (virtual)
   • Antigoni Founta and Lucia Specia
6. • Identifying Causal Influences on Publication Trends and Behavior: A Case Study of the Computational Linguistics Community (virtual)
   • Maria Glenski and Svitlana Volkova