Related papers: Enhancing Document Information Analysis with Multi…

The knowledge that humans hold about a problem often extends far beyond a set of training data and output labels. While the success of deep learning mostly relies on supervised training, important properties cannot be inferred efficiently…

At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…

Binarization of document images is an important pre-processing step in the field of document analysis. Traditional image binarization techniques usually rely on histograms or local statistics to identify a valid threshold to differentiate…

Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal-URLs, leaving open the question of whether other…

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…

Extracting key information from documents, such as receipts or invoices, and preserving the interested texts to structured data is crucial in the document-intensive streamline processes of office automation in areas that includes but not…

Tables stored in databases and tables which are present in web pages and articles account for a large part of semi-structured data that is available on the internet. It then becomes pertinent to develop a modeling approach with large…

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…

In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement. We start by employing a…

Knowledge-enhanced pre-trained models for language representation have been shown to be more effective in knowledge base construction tasks (i.e.,~relation extraction) than language models such as BERT. These knowledge-enhanced language…

With the widespread use of mobile phones and scanners to photograph and upload documents, the need for extracting the information trapped in unstructured document images such as retail receipts, insurance claim forms and financial invoices…

As the Portable Document Format (PDF) file format increases in popularity, research in analysing its structure for text extraction and analysis is necessary. Detecting headings can be a crucial component of classifying and extracting…

Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of…

We present an end-to-end trainable multi-task network that addresses the problem of lexicon-free text extraction from complex documents. This network simultaneously solves the problems of text localization and text recognition and text…

This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are…

The main goal of this research is to produce a useful software for United Nations (UN), that could help to speed up the process of qualifying the UN documents following the Sustainable Development Goals (SDGs) in order to monitor the…

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Document-level event extraction is a long-standing challenging information retrieval problem involving a sequence of sub-tasks: entity extraction, event type judgment, and event type-specific multi-event extraction. However, addressing the…

In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better…

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the…