Related papers: Robust PDF Document Conversion Using Recurrent Neu…
We propose a simple, data-efficient pipeline that augments an implicit reconstruction network based on neural SDF-based CAD parts with a part-segmentation head trained under PartField-generated supervision. Unlike methods tied to fixed…
In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting…
Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications…
Contemporary natural language processing (NLP) revolves around learning from latent document representations, generated either implicitly by neural language models or explicitly by methods such as doc2vec or similar. One of the key…
Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…
Pre-trained contextual language models such as BERT, GPT, and XLnet work quite well for document retrieval tasks. Such models are fine-tuned based on the query-document/query-passage level relevance labels to capture the ranking signals.…
Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient…
The increasing prevalence of malicious Portable Document Format (PDF) files necessitates robust and comprehensive feature extraction techniques for effective detection and analysis. This work presents a unified framework that integrates…
State-of-the-art systems in deep question answering proceed as follows: (1) an initial document retrieval selects relevant documents, which (2) are then processed by a neural network in order to extract the final answer. Yet the exact…
Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks. In this paper, we propose Contextual Recurrent Units (CRU) for enhancing…
The number of scientific papers has increased rapidly in recent years. How to make good use of scientific papers for research is very important. Through the high-quality classification of scientific papers, researchers can quickly find the…
Extracting structured data from HTML documents is a long-studied problem with a broad range of applications like augmenting knowledge bases, supporting faceted search, and providing domain-specific experiences for key verticals like…
Many document types use intrinsic, convention-driven structures that serve to encode precise and structured information, such as the conventions governing engineering drawings. However, many state-of-the-art approaches treat document…
Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks. However, they are limited by their - (i) inability to learn cross-modal…
Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with…
Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating…
Research has shown that Convolutional Neural Networks (CNN) can be effectively applied to text classification as part of a predictive coding protocol. That said, most research to date has been conducted on data sets with short documents…
We present a self-contained system for constructing natural language models for use in text compression. Our system improves upon previous neural network based models by utilizing recent advances in syntactic parsing -- Google's SyntaxNet…
As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original…
Knowledge discovery is defined as non-trivial extraction of implicit, previously unknown and potentially useful information from given data. Knowledge extraction from web documents deals with unstructured, free-format documents whose number…