Related papers: Connecting the Dots: Surfacing Structure in Docume…
The massive amounts of digitized historical documents acquired over the last decades naturally lend themselves to automatic processing and exploration. Research work seeking to automatically process facsimiles and extract information…
Mathematical knowledge is a central component in science, engineering, and technology (documentation). Most of it is represented informally, and -- in contrast to published research mathematics -- subject to continual change. Unfortunately,…
The automation of document processing is gaining recent attention due to the great potential to reduce manual work through improved methods and hardware. Neural networks have been successfully applied before - even though they have been…
As the amount of data on the World Wide Web continues to grow exponentially, access to semantically structured information remains limited. The Semantic Web has emerged as a solution to enhance the machine-readability of data, making it…
How to leverage cross-document interactions to improve ranking performance is an important topic in information retrieval (IR) research. However, this topic has not been well-studied in the learning-to-rank setting and most of the existing…
Graphic visual content helps in promoting information communication and inspiration divergence. However, the interpretation of visual content currently relies mainly on humans' personal knowledge background, thereby affecting the quality…
The explosion of scientific literature has made the efficient and accurate extraction of structured data a critical component for advancing scientific knowledge and supporting evidence-based decision-making. However, existing tools often…
Extracting summaries from long documents can be regarded as sentence classification using the structural information of the documents. How to use such structural information to summarize a document is challenging. In this paper, we propose…
Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model…
Scientific knowledge is predominantly stored in books and scientific journals, often in the form of PDFs. However, the PDF format leads to a loss of semantic information, particularly for mathematical expressions. We propose Nougat (Neural…
Mapping clinical documents to standardised clinical vocabularies is an important task, as it provides structured data for information retrieval and analysis, which is essential to clinical research, hospital administration and improving…
Reading Comprehension has received significant attention in recent years as high quality Question Answering (QA) datasets have become available. Despite state-of-the-art methods achieving strong overall accuracy, Multi-Hop (MH) reasoning…
We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such…
Information extraction from scholarly articles is a challenging task due to the sizable document length and implicit information hidden in text, figures, and citations. Scholarly information extraction has various applications in…
Document AI is a growing research field that focuses on the comprehension and extraction of information from scanned and digital documents to make everyday business operations more efficient. Numerous downstream tasks and datasets have been…
Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However,…
Document subject classification is essential for structuring (digital) libraries and allowing readers to search within a specific field. Currently, the classification is typically made by human domain experts. Semi-supervised Machine…
A systematic review identifies and collates various clinical studies and compares data elements and results in order to provide an evidence based answer for a particular clinical question. The process is manual and involves lot of time. A…
The exponential increase in academic publications has made it increasingly difficult for researchers to remain up to date and systematically synthesize knowledge scattered across vast and fragmented research domains. Literature reviews,…
Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored.…