activity
20182022
most citedSafeText: A Benchmark for Exploring Physical Safety in Language Models

3 citations · 4 across the 5 of their papers we have counts for

collaborators

10 papers

cs.CL2022

Legal and Political Stance Detection of SCOTUS Language

Noah Bergam, Emily Allaway, Kathleen McKeown

We analyze publicly available US Supreme Court documents using automated stance detection. In the first phase of our work, we investigate the extent to which the Court's public-fac…

cs.CL20223 cited

SafeText: A Benchmark for Exploring Physical Safety in Language Models

Sharon Levy, Emily Allaway, Melanie Subbiah +4

Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such typ…

cs.CL2022

Seeded Hierarchical Clustering for Expert-Crafted Taxonomies

Anish Saha, Amith Ananthram, Emily Allaway +2

Practitioners from many disciplines (e.g., political science) use expert-crafted taxonomies to make sense of large, unlabeled corpora. In this work, we study Seeded Hierarchical Cl…

cs.CL20221 cited

Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic

António Câmara, Nina Taneja, Tamjeed Azad +2

As natural language processing systems become more widespread, it is necessary to address fairness issues in their implementation and deployment to ensure that their negative impac…

cs.CL2021

Adversarial Learning for Zero-Shot Stance Detection on Social Media

Emily Allaway, Malavika Srikanth, Kathleen McKeown

Stance detection on social media can help to identify and understand slanted news or commentary in everyday life. In this work, we propose a new model for zero-shot stance detectio…

cs.CL2021

Does Putting a Linguist in the Loop Improve NLU Data Collection?

Alicia Parrish, William Huang, Omar Agha +7

Many crowdsourced NLP datasets contain systematic gaps and biases that are identified only after data collection is complete. Identifying these issues from early data samples durin…