arXiv subjects

Benjamin Sowell

Publications and source records attributed to Benjamin Sowell.

5 recordsLinked to original sources

arXiv2026

DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis

In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relations remains challenging in multi-page documents with long-range dependencies and heterogeneous layouts. To address this, we propose a tree-guided and self-regressive framework, termed DOcument Structure Analyzer (DOSA), for inferring relations among page objects and reconstructing document-level semantic trees. DOSA processes documents chunk-by-chunk, fusing visual, textual, and layout features for each page object and predicting hierarchical and ordering relations. The predicted relations are used to incrementally construct a semantic tree, which is then leveraged as structural context to guide inference on subsequent chunks. Experimental results on five benchmarks demonstrate the effectiveness of DOSA, with improvements of up to 4 F1 points and 19 TEDS points on DocHieNet, the most challenging multi-page hierarchy benchmark.

cs.AI↗

arXiv2024

The Design of an LLM-powered Unstructured Analytics System

LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the design of an unstructured analytics system, Aryn, and the tenets and use cases that motivate its design. With Aryn, users specify queries in natural language and the system automatically determines a semantic plan and executes it to compute an answer from a large collection of unstructured documents. At the core of Aryn is Sycamore, a declarative document processing engine, that provides a reliable distributed abstraction called DocSets. Sycamore allows users to analyze, enrich, and transform complex documents at scale. Aryn includes Luna, a query planner that translates natural language queries to Sycamore scripts, and DocParse, which takes raw PDFs and document images, and converts them to DocSets for downstream processing. We show how these pieces come together to achieve better accuracy than RAG on analytics queries over real world reports from the National Transportation Safety Board (NTSB). Also, given current limitations of LLMs, we argue that an analytics system must provide explainability to be practical, and show how Aryn's user interface does this to help build trust.

cs.DB↗

arXiv2012

Minuet: A Scalable Distributed Multiversion B-Tree

Data management systems have traditionally been designed to support either long-running analytics queries or short-lived transactions, but an increasing number of applications need both. For example, online games, socio-mobile apps, and e-commerce sites need to not only maintain operational state, but also analyze that data quickly to make predictions and recommendations that improve user experience. In this paper, we present Minuet, a distributed, main-memory B-tree that supports both transactions and copy-on-write snapshots for in-situ analytics. Minuet uses main-memory storage to enable low-latency transactional operations as well as analytics queries without compromising transaction performance. In addition to supporting read-only analytics queries on snapshots, Minuet supports writable clones, so that users can create branching versions of the data. This feature can be quite useful, e.g. to support complex "what-if" analysis or to facilitate wide-area replication. Our experiments show that Minuet outperforms a commercial main-memory database in many ways. It scales to hundreds of cores and TBs of memory, and can process hundreds of thousands of B-tree operations per second while executing long-running scans.

cs.DB↗

arXiv2010

Behavioral Simulations in MapReduce

In many scientific domains, researchers are turning to large-scale behavioral simulations to better understand important real-world phenomena. While there has been a great deal of work on simulation tools from the high-performance computing community, behavioral simulations remain challenging to program and automatically scale in parallel environments. In this paper we present BRACE (Big Red Agent-based Computation Engine), which extends the MapReduce framework to process these simulations efficiently across a cluster. We can leverage spatial locality to treat behavioral simulations as iterated spatial joins and greatly reduce the communication between nodes. In our experiments we achieve nearly linear scale-up on several realistic simulations. Though processing behavioral simulations in parallel as iterated spatial joins can be very efficient, it can be much simpler for the domain scientists to program the behavior of a single agent. Furthermore, many simulations include a considerable amount of complex computation and message passing between agents, which makes it important to optimize the performance of a single node and the communication across nodes. To address both of these challenges, BRACE includes a high-level language called BRASIL (the Big Red Agent SImulation Language). BRASIL has object oriented features for programming simulations, but can be compiled to a data-flow representation for automatic parallelization and optimization. We show that by using various optimization techniques, we can achieve both scalability and single-node performance similar to that of a hand-coded simulation.

cs.DB↗

arXiv2009

From Declarative Languages to Declarative Processing in Computer Games

Recent work has shown that we can dramatically improve the performance of computer games and simulations through declarative processing: Character AI can be written in an imperative scripting language which is then compiled to relational algebra and executed by a special games engine with features similar to a main memory database system. In this paper we lay out a challenging research agenda built on these ideas. We discuss several research ideas for novel language features to support atomic actions and reactive programming. We also explore challenges for main-memory query processing in games and simulations including adaptive query plan selection, support for parallel architectures, debugging simulation scripts, and extensions for multi-player games and virtual worlds. We believe that these research challenges will result in a dramatic change in the design of game engines over the next decade.

cs.DB↗