Related papers: Improving Structured Text Recognition with Regular…
In text recognition, complex glyphs and tail classes have always been factors affecting model performance. Specifically for Chinese text recognition, the lack of shape-awareness can lead to confusion among close complex characters. Since…
We propose a generalized version of context-sensitivity in term rewriting based on the notion of "forbidden patterns". The basic idea is that a rewrite step should be forbidden if the redex to be contracted has a certain shape and appears…
Artistic text recognition is an extremely challenging task with a wide range of applications. However, current scene text recognition methods mainly focus on irregular text while have not explored artistic text specifically. The challenges…
Although contemporary text-to-image generation models have achieved remarkable breakthroughs in producing visually appealing images, their capacity to generate precise and flexible typographic elements, especially non-Latin alphabets,…
Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…
Extracting information from unstructured text documents is a demanding task, since these documents can have a broad variety of different layouts and a non-trivial reading order, like it is the case for multi-column documents or nested…
Consistency regularization is a commonly used practice to encourage the model to generate consistent representation from distorted input features and improve model generalization. It shows significant improvement on various speech…
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…
Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels.…
Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…
This paper proposes a medical text summarization method based on LongFormer, aimed at addressing the challenges faced by existing models when processing long medical texts. Traditional summarization methods are often limited by short-term…
Regular expressions are pervasive in modern systems. Many real-world regular expressions are inefficient, sometimes to the extent that they are vulnerable to complexity-based attacks, and while much research has focused on detecting…
Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose…
Regular expressions are often ambiguous. We present a novel method based on Brzozowski's derivatives to aid the user in diagnosing ambiguous regular expressions. We introduce a derivative-based finite state transducer to generate parse…
Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied…
Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more…
The task of definition detection is important for scholarly papers, because papers often make use of technical terminology that may be unfamiliar to readers. Despite prior work on definition detection, current approaches are far from being…
Prior knowledge and symbolic rules in machine learning are often expressed in the form of label constraints, especially in structured prediction problems. In this work, we compare two common strategies for encoding label constraints in a…
Many adversarial attacks in NLP perturb inputs to produce visually similar strings ('ergo' $\rightarrow$ '$\epsilon$rgo') which are legible to humans but degrade model performance. Although preserving legibility is a necessary condition for…
Text detection and recognition are essential components of a modern OCR system. Most OCR approaches attempt to obtain accurate bounding boxes of text at the detection stage, which is used as the input of the text recognition stage. We…