Publications

Bias and Fairness

Vinay Prabhu, Ryan Teehan, and Eniko Srivastava. Did they direct the violence or admonish it? A cautionary tale on contronomy, androcentrism and back-translation foibles. Presented at the EACL 2021 Workshop on African NLP Poster Session, where it won a Best Paper Award

Vinay Uday Prabhu, Ryan Teehan, Sanghyun Han, Nicholas Roberts, Eniko Srivastava, Aremu Anuoluwapo, Ọpẹyemi Adémólá, Rohan Bisariya, and Ana Carolina da Hora, ”Directing the violence or admonishing it? A survey of contronymy and androcentrism in Google Translate and some recommendations” Preprint, 2021. https://openreview.net/forum?id=13LjoyYWcaw. Note: This is a significant extension of the workshop paper

Visualization

Vinay Prabhu, Matthew McAteer, and Ryan Teehan, SPICES: Survey Papers as Interactive Cheatsheet Embeddings. Presented at the Workshop Rethinking ML Papers at ICLR 2021. https://openreview.net/forum?id=1sysg9hi3KS

NLP

Kaustubh D. Dhole and 124 others (including Ryan Teehan), “NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation,”, Preprint to be submitted to NAACL, 2021. https://arxiv.org/abs/2112.02721.

Ryan Teehan*, Natasha Seelam*, Oleg Serikov*, Miruna Clinciu*, Shachar Mirkin*, Eliza Szczechla*, and Aaron Gokaslan, “Emergent Structures and Training Dynamics in Large Language Models”, Under Review at ACL Rolling Review. 2021.

Victor Sanh and 41 others (including Ryan Teehan), “Multitask Prompted Training Enables Zero-Shot Task Generalization”, Accepted to ICLR 2022 as a Spotlight paper, 2021. https://arxiv.org/abs/2110.08207.

Shahbuland Matiana*, JR Smith*, Ryan Teehan*, Louis Castricato*, Stella Biderman, Leo Gao, and Spencer Frazier, “Cut the CARP: Fishing for zero-shot story evaluation”. Preprint, 2021. https://arxiv.org/abs/2110.03111.