Journal Article
Shen, Zejiang, Ruochen Zhang, Melissa Dell, Benjamin Lee, Jacob Carlson, and Weining Li. “LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis.” International Conference on Document Analysis and Recognition (Forthcoming). Article PDFAbstract
Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of important innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applications. 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. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digitization pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at .
Shen, Zejiang, Kaixuan Zhang, and Melissa Dell. “A Large Dataset of Historical Japanese Documents with Complex Layouts.” IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (2020): 548-559. DatasetAbstract
Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale. One major hurdle is the lack of large datasets for training robust models. In particular, little training data exist for Asian languages. To this end, we present HJDataset, a Large Dataset of Historical Japanese Documents with Complex Layouts. It contains over 250,000 layout element annotations of seven types. In addition to bounding boxes and masks of the content regions, it also includes the hierarchical structures and reading orders for layout elements. The dataset is constructed using a combination of human and machine efforts. A semi-rule based method is developed to extract the layout elements, and the results are checked by human inspectors. The resulting large-scale dataset is used to provide baseline performance analyses for text region detection using state-of-the-art deep learning models. And we demonstrate the usefulness of the dataset on real-world document digitization tasks. The dataset is available at this https URL.
Dell, Melissa, and Benjamin Olken. “The Development Effects of the Extractive Colonial Economy: The Dutch Cultivation System in Java.” Review of Economic Studies 87, no. 1 (2020): 164-203. Replication files Paper Appendix
Zhang, Kaixuan, Zejiang Shen, Jie Zhou, and Melissa Dell. “Information Extraction from Text Regions with Complex Tabular Structure.” Conference on Neural Information Processing Systems Document Intelligence Workshop (2019). Paper
Dell, Melissa, Benjamin Feigenberg, and Kensuke Teshima. “The Violent Consequences of Trade-Induced Worker Displacement in Mexico.” American Economic Review: Insights 1, no. 1 (2019): 43-58. Paper Appendix Replication Files
Dell, Melissa, and Pablo Querubin. “Nation Building Through Foreign Intervention: Evidence from Discontinuities in Military Strategies.” Quarterly Journal of Economics 133, no. 2 (2018): 701-764. Paper Appendix Replication files
Dell, Melissa, Nathan Lane, and Pablo Querubin. “The Historical State, Local Collective Action, and Economic Development in Vietnam.” Econometrica 86, no. 6 (2018): 2083-2121. Paper Published Appendix Online Appendix Replication files
Dell, Melissa. “Trafficking Networks and the Mexican Drug War.” American Economic Review 105, no. 6 (2015): 1738-1779. Paper Appendix Replication files


Dell, M., B. Jones, and B. Olken. “What Do We Learn from the Weather? The New Climate-Economy Literature.” Journal of Economic Literature (2014). Paper Appendix
Dell, M, B Jones, and B Olken. “Temperature Shocks and Economic Growth: Evidence from the Last Half Century.” American Economic Journal: Macroeconomics 4, no. 3 (2012): 66-95. PDF Online appendix Data/program files
Dell, M, and D Acemoglu. “Productivity Differences Between and Within Countries.” American Economic Journal: Macroeconomics 2, no. 1 (2010): 169–188. PDF Online appendix Data/program files
Dell, M. “The Persistent Effects of Peru's Mining Mita.” Econometrica 78, no. 6 (2010): 1863-1903. PDF Online appendix Spanish translation Data/program files 1 Data/program files 2 Data/program files 3
Dell, M., B. Jones, and B. Olken. “Temperature and Income: Reconciling New Cross-Sectional and Panel Estimates.” American Economic Review Papers and Proceedings 99, no. 2 (2009): 198-204. Paper Online appendix
Working Paper
Shen, Zejiang, Jian Zhao, Melissa Dell, Yaoliang Yu, and Weining Li. “OLALA: Object-Level Active Learning Based Layout Annotation,” Working Paper. PaperAbstract
In layout object detection problems, the ground-truth datasets are constructed by annotating object instances individually. Yet active learning for object detection is typically conducted at the image level, not at the object level. Because objects appear with different frequencies across images, image-level active learning may be subject to over-exposure to common objects. This reduces the efficiency of human labeling. This work introduces an Object-Level Active Learning based Layout Annotation framework, OLALA, which includes an object scoring method and a prediction correction algorithm. The object scoring method estimates the object prediction informativeness considering both the object category and the location. It selects only the most ambiguous object prediction regions within an image for annotators to label, optimizing the use of the annotation budget. For the unselected model predictions, we propose a correction algorithm to rectify two types of potential errors with minor supervision from ground-truths. The human annotated and model predicted objects are then merged as new image annotations for training the object detection models. In simulated labeling experiments, we show that OLALA helps to create the dataset more efficiently and report strong accuracy improvements of the trained models compared to image-level active learning baselines.
Dell, M.Path Dependence in Development: Evidence from the Mexican Revolution,” Working Paper. PDF Data appendix