475 citations · 512 across the 14 of their papers we have counts for
14 papers
Stay on topic with Classifier-Free Guidance
Guillaume Sanchez, Honglu Fan, Alexander Spangher +3
Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrat…
Identifying Informational Sources in News Articles
Alexander Spangher, Nanyun Peng, Jonathan May +1
News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand th…
Sequentially Controlled Text Generation
Alexander Spangher, Xinyu Hua, Yao Ming +1
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structu…
If it Bleeds, it Leads: A Computational Approach to Covering Crime in Los Angeles
Alexander Spangher, Divya Choudhary
Developing and improving computational approaches to covering news can increase journalistic output and improve the way stories are covered. In this work we approach the problem of…
NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge
Alexander Spangher, Xiang Ren, Jonathan May +1
News article revision histories provide clues to narrative and factual evolution in news articles. To facilitate analysis of this evolution, we present the first publicly available…
Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals
Te-Lin Wu, Alex Spangher, Pegah Alipoormolabashi +3
The ability to sequence unordered events is an essential skill to comprehend and reason about real world task procedures, which often requires thorough understanding of temporal co…
"Don't quote me on that": Finding Mixtures of Sources in News Articles
Alexander Spangher, Nanyun Peng, Jonathan May +1
Journalists publish statements provided by people, or \textit{sources} to contextualize current events, help voters make informed decisions, and hold powerful individuals accountab…
Modeling "Newsworthiness" for Lead-Generation Across Corpora
Alexander Spangher, Nanyun Peng, Jonathan May +1
Journalists obtain "leads", or story ideas, by reading large corpora of government records: court cases, proposed bills, etc. However, only a small percentage of such records are i…
StateCensusLaws.org: A Web Application for Consuming and Annotating Legal Discourse Learning
Alexander Spangher, Jonathan May
In this work, we create a web application to highlight the output of NLP models trained to parse and label discourse segments in law text. Our system is built primarily with journa…
NewsEdits: A Dataset of Revision Histories for News Articles (Technical Report: Data Processing)
Alexander Spangher, Jonathan May
News article revision histories have the potential to give us novel insights across varied fields of linguistics and social sciences. In this work, we present, to our knowledge, th…
Multitask Learning for Class-Imbalanced Discourse Classification
Alexander Spangher, Jonathan May, Sz-rung Shiang +1
Small class-imbalanced datasets, common in many high-level semantic tasks like discourse analysis, present a particular challenge to current deep-learning architectures. In this wo…
Analysis of Strategy and Spread of Russia-sponsored Content in the US in 2017
Alexander Spangher, Gireeja Ranade, Besmira Nushi +2
The Russia-based Internet Research Agency (IRA) carried out a broad information campaign in the U.S. before and after the 2016 presidential election. The organization created an ex…
Actionable Recourse in Linear Classification
Berk Ustun, Alexander Spangher, Yang Liu
Machine learning models are increasingly used to automate decisions that affect humans - deciding who should receive a loan, a job interview, or a social service. In such applicati…
Bayesian Nonparametrics in Topic Modeling: A Brief Tutorial
Alexander Spangher
Using nonparametric methods has been increasingly explored in Bayesian hierarchical modeling as a way to increase model flexibility. Although the field shows a lot of promise, infe…