As one of the most representative DL techniques, Transformer architecture has empowered
numerous advanced models, especially the large language models (LLMs) that comprise …

Transformer, a deep neural network architecture, has long dominated the field of natural
language processing and beyond. Nevertheless, the recent introduction of Mamba …

In the post-deep learning era, the Transformer architecture has demonstrated its powerful
performance across pre-trained big models and various downstream tasks. However, the …

Heterogeneous graph neural networks have recently gained attention for long document
summarization, modeling the extraction as a node classification task. Although effective …

The opinions of the US Supreme Court (SCO-TUS) are known for their extensive length,
complex legal language, and lack of titled sections, which pose significant challenges for …

This report examines methods for integrating an extended discourse context in machine
translation, focusing on neural translation methods. Machine translation systems generally …

Automatic text summarization has made a fantastic leap forward in the last five to ten years,
fueled by the rise of deep learning systems. Summarization at large consists in compressing …