相关论文: Transformer-based HTR for Historical Documents

Structured document understanding has attracted considerable attention and made significant progress recently, owing to its crucial role in intelligent document processing. However, most existing related models can only deal with the…

Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on both modern and historical manuscripts in large benchmark datasets. Nonetheless, those models struggle to obtain…

We propose a novel multimodal architecture for Scene Text Visual Question Answering (STVQA), named Layout-Aware Transformer (LaTr). The task of STVQA requires models to reason over different modalities. Thus, we first investigate the impact…

Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TGAT, and APAN ) and require tailored training frameworks…

Recent progress in semantic parsing scarcely considers languages other than English but professional translation can be prohibitively expensive. We adapt a semantic parser trained on a single language, such as English, to new languages and…

The Transformer translation model is easier to parallelize and provides better performance compared to recurrent seq2seq models, which makes it popular among industry and research community. We implement the Neutron in this work, including…

Transformers have been widely applied in text classification. Unfortunately, real-world data contain anomalies and noisy labels that cause challenges for state-of-art Transformers. This paper proposes Protoformer, a novel self-learning…

We present a multi-task learning framework for cross-lingual abstractive summarization to augment training data. Recent studies constructed pseudo cross-lingual abstractive summarization data to train their neural encoder-decoders.…

In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English ASR model and show that transfer learning can be effectively…

This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained…

Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However,…

This paper presents a translation-based knowledge geraph embedding method via efficient relation rotation (TransERR), a straightforward yet effective alternative to traditional translation-based knowledge graph embedding models. Different…

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP…

This article presents the experiments and results obtained by the GRESEL team in the IberLEF 2025 shared task PastReader: Transcribing Texts from the Past. Three types of experiments were conducted with the dual aim of participating in the…

There is an immense quantity of historical and cultural documentation that exists only as handwritten manuscripts. At the same time, performing OCR across scripts and different handwriting styles has proven to be an enormously difficult…

This paper proposes a new method, OFA-OCR, to transfer multimodal pretrained models to text recognition. Specifically, we recast text recognition as image captioning and directly transfer a unified vision-language pretrained model to the…

Many efforts of research are devoted to semantic role labeling (SRL) which is crucial for natural language understanding. Supervised approaches have achieved impressing performances when large-scale corpora are available for resource-rich…

This paper deals with the task of practical and open source Handwritten Text Recognition (HTR) on German medieval manuscripts. We report on our efforts to construct mixed recognition models which can be applied out-of-the-box without any…

We present our demonstration of two machine translation applications to historical documents. The first task consists in generating a new version of a historical document, written in the modern version of its original language. The second…

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…