Publications (22)
Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection
Suchin Gururangan, Dallas Card, Sarah K. Dreier +5
Language models increasingly rely on massive web dumps for diverse text data. However, these sources are rife with undesirable content. As such, resources like Wikipedia, books, an…
Causal Effects of Linguistic Properties
Reid Pryzant, Dallas Card, Dan Jurafsky +2
We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster respons…
Mapping the Podcast Ecosystem with the Structured Podcast Research Corpus
Benjamin Litterer, David Jurgens, Dallas Card
Podcasts provide highly diverse content to a massive listener base through a unique on-demand modality. However, limited data has prevented large-scale computational analysis of th…
With Little Power Comes Great Responsibility
Dallas Card, Peter Henderson, Urvashi Khandelwal +3
Despite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored…
Deep Weighted Averaging Classifiers
Dallas Card, Michael Zhang, Noah A. Smith
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, c…
Friendships, Rivalries, and Trysts: Characterizing Relations between Ideas in Texts
Chenhao Tan, Dallas Card, Noah A. Smith
Understanding how ideas relate to each other is a fundamental question in many domains, ranging from intellectual history to public communication. Because ideas are naturally embed…
Neural Models for Documents with Metadata
Dallas Card, Chenhao Tan, Noah A. Smith
Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore…
Expected Validation Performance and Estimation of a Random Variable's Maximum
Jesse Dodge, Suchin Gururangan, Dallas Card +2
Research in NLP is often supported by experimental results, and improved reporting of such results can lead to better understanding and more reproducible science. In this paper we…
Validating LLMs in social science: Epistemic threats and emerging norms
Meera Desai, Dallas Card, Abigail Z. Jacobs
Large language models (LLMs) are reshaping social science methodology. Researchers increasingly prompt language models to generate quantitative measurements of social concepts, for…
The Costs of Early-career Disciplinary Pivots: Evidence from Ph.D. Admissions
Sidney Xiang, Nicholas David, Dallas Card +3
Scientific innovation often comes from researchers who pivot across disciplines. However, prior work found that established researchers face productivity penalties when pivoting. H…
Modular Domain Adaptation
Junshen K. Chen, Dallas Card, Dan Jurafsky
Off-the-shelf models are widely used by computational social science researchers to measure properties of text, such as sentiment. However, without access to source data it is diff…
The Values Encoded in Machine Learning Research
Abeba Birhane, Pratyusha Kalluri, Dallas Card +3
Machine learning currently exerts an outsized influence on the world, increasingly affecting institutional practices and impacted communities. It is therefore critical that we ques…
Variational Pretraining for Semi-supervised Text Classification
Suchin Gururangan, Tam Dang, Dallas Card +1
We introduce VAMPIRE, a lightweight pretraining framework for effective text classification when data and computing resources are limited. We pretrain a unigram document model as a…
Show Your Work: Improved Reporting of Experimental Results
Jesse Dodge, Suchin Gururangan, Dallas Card +2
Research in natural language processing proceeds, in part, by demonstrating that new models achieve superior performance (e.g., accuracy) on held-out test data, compared to previou…
On Consequentialism and Fairness
Dallas Card, Noah A. Smith
Recent work on fairness in machine learning has primarily emphasized how to define, quantify, and encourage "fair" outcomes. Less attention has been paid, however, to the ethical f…
Detecting Stance in Media on Global Warming
Yiwei Luo, Dallas Card, Dan Jurafsky
Citing opinions is a powerful yet understudied strategy in argumentation. For example, an environmental activist might say, "Leading scientists agree that global warming is a serio…
Framing Social Movements on Social Media: Unpacking Diagnostic, Prognostic, and Motivational Strategies
Julia Mendelsohn, Maya Vijan, Dallas Card +1
Social media enables activists to directly communicate with the public and provides a space for movement leaders, participants, bystanders, and opponents to collectively construct…
You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
Bangzhao Shu, Lechen Zhang, Minje Choi +5
The versatility of Large Language Models (LLMs) on natural language understanding tasks has made them popular for research in social sciences. To properly understand the properties…
On the Opportunities and Risks of Foundation Models
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111
AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…
Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words
Kaitlyn Zhou, Kawin Ethayarajh, Dallas Card +1
Cosine similarity of contextual embeddings is used in many NLP tasks (e.g., QA, IR, MT) and metrics (e.g., BERTScore). Here, we uncover systematic ways in which word similarities e…
When it Rains, it Pours: Modeling Media Storms and the News Ecosystem
Benjamin Litterer, David Jurgens, Dallas Card
Most events in the world receive at most brief coverage by the news media. Occasionally, however, an event will trigger a media storm, with voluminous and widespread coverage lasti…
Substitution-based Semantic Change Detection using Contextual Embeddings
Dallas Card
Measuring semantic change has thus far remained a task where methods using contextual embeddings have struggled to improve upon simpler techniques relying only on static word vecto…