Related papers: A Neural Edge-Editing Approach for Document-Level …

Many real world systems need to operate on heterogeneous information networks that consist of numerous interacting components of different types. Examples include systems that perform data analysis on biological information networks; social…

Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods. While there is an abundance of textual information throughout the web and many existing knowledge bases, aligning information…

The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine…

Event extraction is a classic task in natural language processing with wide use in handling large amount of yet rapidly growing financial, legal, medical, and government documents which often contain multiple events with their elements…

Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the…

Tables are widely used in several types of documents since they can bring important information in a structured way. In scientific papers, tables can sum up novel discoveries and summarize experimental results, making the research…

In this work, we propose a novel knowledge graph alignment technique based upon string edit distance that exploits the type information between entities and can find similarity between relations of any arity

Text summarization aims to compress a textual document to a short summary while keeping salient information. Extractive approaches are widely used in text summarization because of their fluency and efficiency. However, most of existing…

This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to use multiple sub-graphs to learn rich node representations in…

Graph generation is integral to various engineering and scientific disciplines. Nevertheless, existing methodologies tend to overlook the generation of edge attributes. However, we identify critical applications where edge attributes are…

This paper investigates the Relation Extraction task in documents by benchmarking two different neural network models: a multi-modal language model (LayoutXLM) and a Graph Neural Network: Edge Convolution Network (ECN). For this benchmark,…

Extracting information from tables in documents presents a significant challenge in many industries and in academic research. Existing methods which take a bottom-up approach of integrating lines into cells and rows or columns neglect the…

Relation extraction (RE) is the task of extracting relations between entities in text. Most RE methods extract relations from free-form running text and leave out other rich data sources, such as tables. We explore RE from the perspective…

Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for…

The aim of edge editing or modification problems is to change a given graph by adding and deleting of a small number of edges in order to satisfy a certain property. We consider the Edge Editing to a Connected Graph of Given Degrees problem…

A partial edge drawing (PED) of a graph is a variation of a node-link diagram. PED draws a link, which is a partial visual representation of an edge, and reduces visual clutter of the node-link diagram. However, more time is required to…

We present an end-to-end, multimodal, fully convolutional network for extracting semantic structures from document images. We consider document semantic structure extraction as a pixel-wise segmentation task, and propose a unified model…

Document-level relation extraction (DocRE) aims to extract relations between entities from unstructured document text. Compared to sentence-level relation extraction, it requires more complex semantic understanding from a broader text…

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful…

Graph Neural Networks (GNNs) have proven to excel in predictive modeling tasks where the underlying data is a graph. However, as GNNs are extensively used in human-centered applications, the issue of fairness has arisen. While edge deletion…