Share This Author
The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
A visual content recognition model trained on bounding box annotations of photographs, illustrations, maps, comics, and editorial cartoons collected as part of the Library of Congress's Beyond Words crowdsourcing initiative and augmented with additional annotations including those of headlines and advertisements is described.
Improved Point-source Detection in Crowded Fields Using Probabilistic Cataloging
Cataloging is challenging in crowded fields because sources are extremely covariant with their neighbors and blending makes even the number of sources ambiguous. We present the first optical…
LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
- Zejiang Shen, Ruochen Zhang, Melissa Dell, B. Lee, Jacob Carlson, Weining Li
- Computer ScienceICDAR
- 29 March 2021
The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout detection, character recognition, and many other document processing tasks and incorporates a community platform for sharing both pre-trained models and full document digitization pipelines.
The Newspaper Navigator Dataset: Extracting Headlines and Visual Content from 16 Million Historic Newspaper Pages in Chronicling America
The pipeline that utilizes this deep learning model to extract 7 classes of visual content, complete with textual content such as captions derived from the METS/ALTO OCR, as well as image embeddings is described and the resulting Newspaper Navigator dataset is described.
Line detection in binary document scans: A case study with the international tracing service archives
- B. Lee
- Computer ScienceIEEE International Conference on Big Data (Big…
- 1 December 2017
This short paper presents the in-progress work on a method of line detection in binary document scans that is capable of differentiating solid and dotted lines, and represents the first step in this proposed pipeline of classifying International Tracing Service documents by line structure.
Explanation-Based Tuning of Opaque Machine Learners with Application to Paper Recommendation
This paper introduces LIMEADE, a general framework for tuning an arbitrary machine learning model based on an explanation of the model's prediction, and applies it to Semantic Sanity, a neural recommender system for scientific papers, showing that the framework leads to significantly higher perceived user control, trust, and satisfaction.
Newspaper Navigator: Open Faceted Search for 1.5 Million Images
This demo presents Newspaper Navigator, an open faceted search system for 1.5 million historic newspaper photographs, which empowers users to specify their own facets in an open-domain fashion during the search process by selecting relevant examples and iteratively training a machine learner.
Machine learning, template matching, and the International Tracing Service digital archive: Automating the retrieval of death certificate reference cards from 40 million document scans
- B. Lee
- Computer ScienceDigit. Scholarsh. Humanit.
- 9 November 2018
This work adopts template matching and machine learning to automate the retrieval of death certificate reference cards from the ITS digital archive, and demonstrates the efficacy of this method on a test set of 22,117 hand-classified cards, reporting 100% precision and 100% recall.
Compounded Mediation: A Data Archaeology of the Newspaper Navigator Dataset
- B. Lee
- SociologyDigit. Humanit. Q.
The increasing roles of machine learning and artificial intelligence in the construction of cultural heritage and humanities datasets necessitate critical examination of the myriad biases introduced…
LIMEADE: A General Framework for Explanation-Based Human Tuning of Opaque Machine Learners
This paper introduces LIMEADE, a general framework for tuning an arbitrary machine learning model based on an explanation of the model’s prediction and uncovers a tradeoff between canonical greedy explanations and diverse explanations that better facilitate human tuning.