Related papers: Message Passing Attention Networks for Document Un…

Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural…

Multi-hop reading comprehension across multiple documents attracts much attention recently. In this paper, we propose a novel approach to tackle this multi-hop reading comprehension problem. Inspired by human reasoning processing, we…

Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising…

Message passing neural networks have recently evolved into a state-of-the-art approach to representation learning on graphs. Existing methods perform synchronous message passing along all edges in multiple subsequent rounds and consequently…

Graph Neural Networks (GNNs) have become a prominent approach to machine learning with graphs and have been increasingly applied in a multitude of domains. Nevertheless, since most existing GNN models are based on flat message-passing…

In many ways, graphs are the main modality of data we receive from nature. This is due to the fact that most of the patterns we see, both in natural and artificial systems, are elegantly representable using the language of graph structures.…

Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this…

We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attention mechanism in…

Mind-map generation aims to process a document into a hierarchical structure to show its central idea and branches. Such a manner is more conducive to understanding the logic and semantics of the document than plain text. Recently, a…

A hallmark of graph neural networks is their ability to distinguish the isomorphism class of their inputs. This study derives hardness results for the classification variant of graph isomorphism in the message-passing model (MPNN). MPNN…

In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting…

Neural networks efficiently encode learned information within their parameters. Consequently, many tasks can be unified by treating neural networks themselves as input data. When doing so, recent studies demonstrated the importance of…

Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer). Despite the…

Researchers have relegated natural language processing tasks to Transformer-type models, particularly generative models, because these models exhibit high versatility when performing generation and classification tasks. As the size of these…

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document…

The message passing framework is the foundation of the immense success enjoyed by graph neural networks (GNNs) in recent years. In spite of its elegance, there exist many problems it provably cannot solve over given input graphs. This has…

Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and…

Graph Neural Networks (GNNs) have attracted increasing attention in recent years and have achieved excellent performance in semi-supervised node classification tasks. The success of most GNNs relies on one fundamental assumption, i.e., the…

Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by applying a non-uniform score (attending) to the features. Recent…

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local…