Graph representation learning is crucial for many real-world applications (eg social relation
analysis). A fundamental problem for graph representation learning is how to effectively …

Extractive summarization for long documents is challenging due to the extended structured
input context. The long-distance sentence dependency hinders cross-sentence relations …

A fundamental challenge of bipartite graph representation learning is how to extract
informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to …

Text summarization holds significance in the realm of natural language processing as it
expedites the extraction of crucial information from extensive textual content. The paper …

Multi-layered inter-dependent networks have emerged in a wealth of high-impact application
domains. Cross-layer dependency inference, which aims to predict the dependencies …

Graph self-supervised learning has attracted plenty of attention in recent years. However,
most existing methods are designed for homogeneous graphs yet not tailored for bipartite …

Graphs are powerful representations for relations among objects, which have attracted
plenty of attention in both academia and industry. A fundamental challenge for graph …

With the success of the sequence-to-sequence model, end-to-end task-oriented dialogue
systems (EToDs) have obtained remarkable progress. However, most existing EToDs are …

Although automatic text summarization (ATS) has been researched for several decades, the
application of graph neural networks (GNNs) to this task started relatively recently. In this …

In recent years, deep learning has revolutionized natural language processing (NLP) by
enabling the development of models that can learn complex representations of language …