ACL Findings2021
Few-Shot Upsampling for Protest Size Detection
Andrew Halterman, Benjamin J. Radford
Abstract
We propose a new task and dataset for a common problem in social science research: "upsampling" coarse document labels to finegrained labels or spans. We pose the problem in a question answering format, with the answers providing the fine-grained labels. We provide a benchmark dataset and baselines on a socially impactful task: identifying the exact crowd size at protests and demonstrations in the United States given only orderof-magnitude information about protest attendance, a very small sample of fine-grained examples, and English-language news text. We evaluate several baseline models, including zero-shot results from rule-based and questionanswering models, few-shot models fine-tuned on a small set of documents, and weakly supervised models using a larger set of coarselylabeled documents. We find that our rulebased model initially outperforms a zero-shot pre-trained transformer language model but that further fine-tuning on a very small subset of 25 examples substantially improves out-ofsample performance. We also demonstrate a method for fine-tuning the transformer span on only the coarse labels that performs similarly to our rule-based approach. This work will contribute to social scientists' ability to generate data to understand the causes and successes of collective action.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on2
Related papers
- The Benefits of Label-Description Training for Zero-Shot Text ClassificationLingyu Gao, Debanjan Ghosh, Kevin GimpelEMNLP 2023 · 6 citations
- Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of EmbeddingsLiyan Xu, Zhenlin Su, Mo Yu, Jiangnan Li et al.EMNLP Findings 2025 · 1 citation
- Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt CollectionsRuiqi Zhong, Kristy Lee, Zheng Zhang, Dan KleinEMNLP Findings 2021 · 101 citations
- Finetuning LLMs for Human Behavior Prediction in Social Science ExperimentsAkaash Kolluri, Shengguang Wu, Joon Sung Park, Michael S. BernsteinEMNLP 2025 · 12 citations
- POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex EventsSai Vallurupalli, Sayontan Ghosh, Katrin Erk, Niranjan Balasubramanian et al.EMNLP 2022
