8 papers
A Unifying Framework for Robust and Efficient Inference with Unstructured Data
Jacob Carlson, Melissa Dell
To analyze unstructured data (text, images, audio, video), economists typically first extract low-dimensional structured features with a neural network. Neural networks do not make…
News Deja Vu: Connecting Past and Present with Semantic Search
Brevin Franklin, Emily Silcock, Abhishek Arora +2
Social scientists and the general public often analyze contemporary events by drawing parallels with the past, a process complicated by the vast, noisy, and unstructured nature of…
Efficient OCR for Building a Diverse Digital History
Jacob Carlson, Tom Bryan, Melissa Dell
Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence archite…
LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models
Abhishek Arora, Melissa Dell
Linking information across sources is fundamental to a variety of analyses in social science, business, and government. While large language models (LLMs) offer enormous promise fo…
Contrastive Entity Coreference and Disambiguation for Historical Texts
Abhishek Arora, Emily Silcock, Leander Heldring +1
Massive-scale historical document collections are crucial for social science research. Despite increasing digitization, these documents typically lack unique cross-document identif…
Linking Representations with Multimodal Contrastive Learning
Abhishek Arora, Xinmei Yang, Shao-Yu Jheng +1
Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record…