Related papers: Digital Editions as Distant Supervision for Layout…
In this paper, we model the document revision detection problem as a minimum cost branching problem that relies on computing document distances. Furthermore, we propose two new document distance measures, word vector-based Dynamic Time…
When approaching the semantic segmentation of overhead imagery in the decimeter spatial resolution range, successful strategies usually combine powerful methods to learn the visual appearance of the semantic classes (e.g. convolutional…
In essence, embedding algorithms work by optimizing the distance between a word and its usual context in order to generate an embedding space that encodes the distributional representation of words. In addition to single words or word…
Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…
Writing and reading are dynamic processes. As an author composes a text, a sequence of words is produced. This sequence is one that, the author hopes, causes a revisitation of certain thoughts and ideas in others. These processes of…
The production of digital critical editions of texts using TEI is now a widely-adopted procedure within digital humanities. The work described in this paper extends this approach to the publication of gnomologia (anthologies of wise…
We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical guarantees. Our method builds digital ``marks'' using invisible Unicode…
Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with…
We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…
Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large…
This paper presents an intertemporal bimodal network to analyze the evolution of the semantic content of a scientific field within the framework of topic modeling, namely using the Latent Dirichlet Allocation (LDA). The main contribution is…
This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and…
Archaeology is an intriguing domain for computer vision. It suffers not only from shortage in (labeled) data, but also from highly-challenging data, which is often extremely abraded and damaged. This paper proposes a novel semi-supervised…
Extracting coherent and human-understandable themes from large collections of unstructured historical newspaper archives presents significant challenges due to topic evolution, Optical Character Recognition (OCR) noise, and the sheer volume…
Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution…
We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to real-world document segmentation. DDR renders pseudo-document…
Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…
Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However, the best way to harness the perceptual knowledge of…
Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among…
A principal barrier to training temporal relation extraction models in new domains is the lack of varied, high quality examples and the challenge of collecting more. We present a method of automatically collecting distantly-supervised…