Related papers: E-books and Graphics with LaTeXML
Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications. Current state-of-the-art methods focus on scanned documents with approaches combining computer vision, natural language…
Diagrams play a crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and…
Large language models (LLMs) have shown exceptional performance on a variety of natural language tasks. Yet, their capabilities for HTML understanding -- i.e., parsing the raw HTML of a webpage, with applications to automation of web-based…
This work explores a closure task in comics, a medium where visual and textual elements are intricately intertwined. Specifically, Text-cloze refers to the task of selecting the correct text to use in a comic panel, given its neighboring…
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method. Recent work demonstrates that adapting models using reading comprehension data formatted by…
Transforming XML documents with conventional XML languages, like XSL-T, is disadvantageous because there is too lax abstraction on the target language and it is rather difficult to recognize rule-oriented transformations. Prolog as a…
Our winning submission to the 2014 Kaggle competition for Large Scale Hierarchical Text Classification (LSHTC) consists mostly of an ensemble of sparse generative models extending Multinomial Naive Bayes. The base-classifiers consist of…
The number of published PDF documents has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. In this paper, we present a novel approach to document…
Text-to-image generation has greatly advanced content creation, yet accurately rendering visual text remains a key challenge due to blurred glyphs, semantic drift, and limited style control. Existing methods often rely on pre-rendered glyph…
Inspired by recent work on compression with and for young humans, the success of transform-based approaches to information processing, and the rise of powerful language-based AI, we propose \emph{textual transform coding}. It shares some of…
LIBS2ML is a library based on scalable second order learning algorithms for solving large-scale problems, i.e., big data problems in machine learning. LIBS2ML has been developed using MEX files, i.e., C++ with MATLAB/Octave interface to…
Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…
Proponents of the programming language Prolog share the opinion Prolog is more appropriate for transforming XML-documents as other well-established techniques and languages like XSLT. In order to clarify this position this work proposes a…
XML is a standard and universal language for representing information. XML processing is supported by two key frameworks: DOM and SAX. SAX is efficient, but leaves the developer to encode much of the processing. This paper introduces a…
Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well?…
Library learning compresses a given corpus of programs by extracting common structure from the corpus into reusable library functions. Prior work on library learning suffers from two limitations that prevent it from scaling to larger, more…
In recent years, protein-text models have gained significant attention for their potential in protein generation and understanding. Current approaches focus on integrating protein-related knowledge into large language models through…
The field of scientific publishing that is served by LaTeX is increasingly dependent on the availability of metadata about publications. We discuss how to use LaTeX classes and BibTeX styles to curate metadata throughout the life cycle of a…
Converting data from machine-unreadable formats like PDFs into Markdown has the potential to enhance the accessibility of scientific research. Existing end-to-end decoder transformer models can transform screenshots of PDFs into Markdown,…
Correctly parsing mathematical formulas from PDFs is critical for training large language models and building scientific knowledge bases from academic literature, yet existing benchmarks either exclude formulas entirely or lack…