Business documents are central to the operation of all organizations, and they come in all shapes and sizes: project reports, planning documents, technical specifications, financial statements, meeting minutes, legal agreements, contracts, resumes, purchase orders, invoices, and many more. The ability to read, understand and interpret these documents, referred to here as Document Intelligence (DI), is challenging due to not only many domains of knowledge involved, but also their complex formats and structures, internal and external cross references deployed, and even less-than-ideal quality of scans and OCR oftentimes performed on them. This workshop aims to explore and advance the current state of research and practice in answering these challenges.

We present KaaPa (Knowledge Aware Answers from Pdf Analysis), an integrated solution for machine reading comprehension over both text and tables extracted from PDFs. KaaPa enables interactive question refinement using facets generated from an automatically induced Knowledge Graph. In addition it provides a concise summary of the supporting evidence for the provided answers by aggregating information across multiple sources. KaaPa can be applied consistently to any collection of documents in English with zero domain adaptation effort. We showcase the use of KaaPa for QA on scientific literature using the COVID-19 Open Research Dataset.

Business documents are central to the operation of all organizations, and they come in all shapes and sizes: project reports, planning documents, technical specifications, financial statements, meeting minutes, legal agreements, contracts, resumes, purchase orders, invoices, and many more. The ability to read, understand and interpret these documents, referred to here as Document Intelligence (DI), is challenging due to not only many domains of knowledge involved, but also their complex formats and structures, internal and external cross references deployed, and even less-than-ideal quality of scans and OCR oftentimes performed on them. This workshop aims to explore and advance the current state of research and practice in answering these challenges.

Documents are often used for knowledge sharing and preservation in business and science, within which are tables that capture most of the critical data. Unfortunately, most documents are stored and distributed as PDF or scanned images, which fail to preserve logical table structure. Recent vision-based deep learning approaches have been proposed to address this gap, but most still cannot achieve state-of-the-art results. We present Global Table Extractor (GTE), a vision-guided systematic framework for joint table detection and cell structured recognition, which could be built on top of any object detection model. With GTE-Table, we invent a new penalty based on the natural cell containment constraint of tables to train our table network aided by cell location predictions. GTE-Cell is a new hierarchical cell detection network that leverages table styles. Further, we design a method to automatically label table and cell structure in existing documents to cheaply create a large corpus of training and test data. We use this to enhance PubTabNet with cell labels and create FinTabNet, real-world and complex scientific and financial datasets with detailed table structure annotations to help train and test structure recognition. Our framework surpasses previous state-of-the-art results on the ICDAR 2013 and ICDAR 2019 table competition in both table detection and cell structure recognition. Further experiments demonstrate a greater than 45% improvement in cell structure recognition when compared to a vanilla RetinaNet object detection model in our new out-of-domain FinTabNet.

Valuable high-precision data are often published in the form of tables in both scientific and business documents. While humans can easily identify, interpret and contextualize tables, developing general-purpose automated techniques for extraction of information from tables is difficult due to the wide variety of table formats employed across corpora. To extract useful data from tables, data cells must be correctly extracted and linked to all relevant headers, units of measure and in-text references. Table extraction involves identifying the border and cell structure for each document table, while table understanding provides context by linking cells with semantic information inside and outside the table, such as row and column headers, footnotes, titles, and references in surrounding text. The objective of this tutorial is to provide a detailed synopsis of existing approaches for table extraction and understanding, highlight open research problems, and provide an overview of potential applications.

Convolutional neural networks are shown to achieve breakthrough performance for the task of single image super resolution (SISR) for natural images. These state-of-the-art (SOA) networks have been adapted to the task of single text image super resolution and have been shown to boost the optical character recognition (OCR) performance. However, these approaches depend on variations of the standard mean squared error (MSE) loss in order to train the SR network for improving the text image quality which does not guarantee optimal OCR performance. In this paper, we propose to combine the OCR performance into the loss function during network training. This results in the generation of high resolution text images that achieve high OCR performance that is comparable to the ground truth high-resolution text images and surpassing those of the SOA baseline results. We define novel intuitive metrics to capture the improvement in the OCR performance and provide extensive experiments to qualitatively and quantitatively assess improvement in the results of our proposed approach against the SOA baselines on the standard UNLV dataset.

DSMM 2019 will explore the challenges of macro-modeling with financial and economic datasets. The workshop will also showcase the 2019 Financial Entity Identification and Information Integration (FEIII) Challenge which involves two challenge tasks, one over small business data and the other over customs data for shipping manifests.

We develop a unifying approach to declarative entity linking by introducing the notion of an entity linking framework and an accompanying notion of the certain links in such a framework. In an entity linking framework, logic-based constraints are used to express properties of the desired link relations in terms of source relations and, possibly, in terms of other link relations. The definition of the certain links in such a framework makes use of weighted repairs and consistent answers in inconsistent databases. We demonstrate the modeling capabilities of this approach by showing that numerous concrete entity linking scenarios can be cast as such entity linking frameworks for suitable choices of constraints and weights. By using the certain links as a measure of expressive power, we investigate the relative expressive power of several entity linking frameworks and obtain sharp comparisons. In particular, we show that we gain expressive power if we allow constraints that capture non-recursive collective entity resolution, where link relations may depend on other link relations (and not just on source relations). Moreover, we show that an increase in expressive power also takes place when we allow constraints that incorporate preferences as an additional mechanism for expressing "goodness" of links.

We introduce and develop a declarative framework for entity linking and, in particular, for entity resolution. As in some earlier approaches, our framework is based on a systematic use of constraints. However, the constraints we adopt are link-to-source constraints, unlike in earlier approaches where source-to-link constraints were used to dictate how to generate links. Our approach makes it possible to focus entirely on the intended properties of the outcome of entity linking, thus separating the constraints from any procedure of how to achieve that outcome. The core language consists of link-to-source constraints that specify the desired properties of a link relation in terms of source relations and built-in predicates such as similarity measures. A key feature of the link-to-source constraints is that they employ disjunction, which enables the declarative listing of all the reasons two entities should be linked. We also consider extensions of the core language that capture collective entity resolution by allowing interdependencies among the link relations. We identify a class of “good” solutions for entity-linking specifications, which we call maximum-value solutions and which capture the strength of a link by counting the reasons that justify it. We study natural algorithmic problems associated with these solutions, including the problem of enumerating the “good” solutions and the problem of finding the certain links, which are the links that appear in every “good” solution. We show that these problems are tractable for the core language but may become intractable once we allow interdependencies among the link relations. We also make some surprising connections between our declarative framework, which is deterministic, and probabilistic approaches such as ones based on Markov Logic Networks.

Meta learning techniques such as cross-validation and ensemble learning are crucial for applying machine learning to real-world use cases. These techniques first generate samples from input data, and then train and evaluate machine learning models on these samples. For meta learning on large datasets, the efficient generation of samples becomes problematic, especially when the data is stored distributed in a block-partitioned representation, and processed on a shared-nothing cluster. We present a novel, parallel algorithm for efficient sample generation from large, block-partitioned datasets in a shared-nothing architecture. This algorithm executes in a single pass over the data, and minimizes inter-machine communication. The algorithm supports a wide variety of sample generation techniques through an embedded user-defined sampling function. We illustrate how to implement distributed sample generation for popular meta learning techniques such as hold-out tests, k-fold cross-validation, and bagging, using our algorithm and present an experimental evaluation on datasets with billions of datapoints.

The aim of this paper is to introduce and develop a truly declarative framework for entity linking and, in particular, for entity resolution. As in some earlier approaches, our framework is based on the systematic use of constraints. However, the constraints we adopt are link-to-source constraints, unlike in earlier approaches where source-to-link constraints were used to dictate how to generate links. Our approach makes it possible to focus entirely on the intended properties of the outcome of entity linking, thus separating the constraints from any procedure of how to achieve that outcome. The core language consists of link-to-source constraints that specify the desired properties of a link relation in terms of source relations and built-in predicates such as similarity measures. A key feature of the link-to-source constraints is that they employ disjunction, which enables the declarative listing of all the reasons as to why two entities should be linked. We also consider extensions of the core language that capture collective entity resolution, by allowing inter-dependence between links. We identify a class of "good" solutions for entity linking specifications, which we call maximum-value solutions and which capture the strength of a link by counting the reasons that justify it. We study natural algorithmic problems associated with these solutions, including the problem of enumerating the "good" solutions, and the problem of finding the certain links, which are the links that appear in every "good" solution. We show that these problems are tractable for the core language, but may become intractable once we allow inter-dependence between link relations. We also make some surprising connections between our declarative framework, which is deterministic, and probabilistic approaches such as ones based on Markov Logic Networks.

SystemML aims at declarative, large-scale machine learning (ML) on top of MapReduce, where high-level ML scripts with R-like syntax are compiled to programs of MR jobs. The declarative specification of ML algorithms enables---in contrast to existing large-scale machine learning libraries---automatic optimization. SystemML's primary focus is on data parallelism but many ML algorithms inherently exhibit opportunities for task parallelism as well. A major challenge is how to efficiently combine both types of parallelism for arbitrary ML scripts and workloads. In this paper, we present a systematic approach for combining task and data parallelism for large-scale machine learning on top of MapReduce. We employ a generic Parallel FOR construct (ParFOR) as known from high performance computing (HPC). Our core contributions are (1) complementary parallelization strategies for exploiting multi-core and cluster parallelism, as well as (2) a novel cost-based optimization framework for automatically creating optimal parallel execution plans. Experiments on a variety of use cases showed that this achieves both efficiency and scalability due to automatic adaptation to ad-hoc workloads and unknown data characteristics.

Analytics on big data range from passenger volume prediction in transportation to customer satisfaction in automotive diagnostic systems, and from correlation analysis in social media data to log analysis in manufacturing. Expressing and running these analytics for varying data characteristics and at scale is challenging. To address these challenges, SystemML implements a declarative, high-level language using an R-like syntax extended with machine-learning-specific constructs, that is compiled to a MapReduce runtime [2]. The language is rich enough to express a wide class of statistical, predictive modeling and machine learning algorithms (Fig. 1). We chose robust algorithms that scale to large, and potentially sparse data with many features.

OpenII (openintegration.org) is a collaborative effort to create a suite of open-source tools for information integration (II). The project is leveraging the latest developments in II research to create a platform on which integration tools can be built and further research conducted. In addition to a scalable, extensible platform, OpenII includes industrial-strength components developed by MITRE, Google, UC-Irvine, and UC-Berkeley that interoperate through a common repository in order to solve II problems. Components of the toolkit have been successfully applied to several large-scale US government II challenges.

Large, dynamic, and ad-hoc organizations must frequently initiate data integration and sharing efforts with insufficient awareness of how organizational data sources are related. Decision makers need to reason about data model interactions much as they do about data instance interactions in OLAP: at multiple levels of granularity. We demonstrate an integrated environment for exploring schema similarity across multiple resolutions. Users visualize and interact with clusters of related schemas using a tool named Affinity. Within any cluster, users may drill-down to examine the extent and content of schema overlap. Further drill down enables users to explore fine-grained element-level correspondences between between two selected schemas.

We present a new algorithm for mining maximal frequent itemsets from a transactional database. The search strategy of the algorithm integrates a depth-first traversal of the itemset lattice with effective pruning mechanisms that significantly improve mining performance. Our implementation for support counting combines a vertical bitmap representation of the data with an efficient bitmap compression scheme. In a thorough experimental analysis, we isolate the effects of individual components of MAFIA including search space pruning techniques and adaptive compression. We also compare our performance with previous work by running tests on very different types of data sets. Our experiments show that MAFIA performs best when mining long itemsets and outperforms other algorithms on dense data by a factor of three to 30.

We present a new algorithm for mining maximal frequent itemsets from a transactional database. Our algorithm is especially efficient when the itemsets in the database are very long. The search strategy of our algorithm integrates a depth-first traversal of the itemset lattice with effective pruning mechanisms. Our implementation of the search strategy combines a vertical bitmap representation of the database with an efficient relative bitmap compression schema. In a thorough experimental analysis of our algorithm on real data, we isolate the effect of the individual components of the algorithm. Our performance numbers show that our algorithm outperforms previous work by a factor of three to five.