Related papers: CLOCR-C: Context Leveraging OCR Correction with Pr…

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot…

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…

Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly…

Optical Character Recognition has been a challenging field in the advent of digital computers. It is needed where information is to be readable both to humans and machines. The process of OCR is composed of a set of pre and post processing…

Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into…

Despite significant advancements in Large Vision Language Models (LVLMs), a gap remains, particularly regarding their interpretability and how they locate and interpret textual information within images. In this paper, we explore various…

An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of…

The integration of contextual information has significantly enhanced the performance of large language models (LLMs) on knowledge-intensive tasks. However, existing methods often overlook a critical challenge: the credibility of context…

Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data.…

Selecting high-quality data for pre-training is crucial in shaping the downstream task performance of language models. A major challenge lies in identifying this optimal subset, a problem generally considered intractable, thus necessitating…

Out-of-context reasoning (OOCR) is a phenomenon in which fine-tuned LLMs exhibit surprisingly deep out-of-distribution generalization. Rather than learning shallow heuristics, they implicitly internalize and act on the consequences of…

For the bachelor project 2021 of Professor Lippert's research group, handwritten entries of historical patient records needed to be digitized using Optical Character Recognition (OCR) methods. Since the data will be used in the future, a…

In this paper, we propose a data augmentation framework for Optical Character Recognition (OCR). The proposed framework is able to synthesize new viewing angles and illumination scenarios, effectively enriching any available OCR dataset.…

Scientific articles published prior to the "age of digitization" (~1997) require Optical Character Recognition (OCR) to transform scanned documents into machine-readable text, a process that often produces errors. We develop a pipeline for…

Spelling irregularities, known now as spelling mistakes, have been found for several centuries. As humans, we are able to understand most of the misspelled words based on their location in the sentence, perceived pronunciation, and context.…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

In recent years, learned image compression (LIC) technologies have surpassed conventional methods notably in terms of rate-distortion (RD) performance. Most present learned techniques are VAE-based with an autoregressive entropy model,…

This paper investigates the presence of OCR-sensitive neurons within the Transformer architecture and their influence on named entity recognition (NER) performance on historical documents. By analysing neuron activation patterns in response…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

With the rapid development of OCR technology, mixed-scene text recognition has become a key technical challenge. Although deep learning models have achieved significant results in specific scenarios, their generality and stability still…