Related papers: Attention-Based Capsule Networks with Dynamic Rout…

Understanding the inner workings of neural networks is essential for enhancing model performance and interpretability. Current research predominantly focuses on examining the connection between individual neurons and the model's final…

Form understanding is a challenging problem which aims to recognize semantic entities from the input document and their hierarchical relations. Previous approaches face significant difficulty dealing with the complexity of the task, thus…

Deep learning models for tabular data typically do not allow for imposing a graph of external dependencies between samples, which can be useful for accounting for relatedness in tasks such as treatment effect estimation. Graph neural…

Our work is motivated by and illustrated with application of association networks in computational biology, specifically in the context of gene/protein regulatory networks. Association networks represent systems of interacting elements,…

The joint entity and relation extraction task aims to extract all relational triples from a sentence. In essence, the relational triples contained in a sentence are unordered. However, previous seq2seq based models require to convert the…

We propose a novel neural memory network based framework for future action sequence forecasting. This is a challenging task where we have to consider short-term, within sequence relationships as well as relationships in between sequences,…

Convolutional neural networks (CNNs) achieve translational invariance by using pooling operations. However, the operations do not preserve the spatial relationships in the learned representations. Hence, CNNs cannot extrapolate to various…

In-context learning with attention enables large neural networks to make context-specific predictions by selectively focusing on relevant examples. Here, we adapt this idea to supervised learning procedures such as lasso regression and…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Temporal information extraction plays a critical role in natural language understanding. Previous systems have incorporated advanced neural language models and have successfully enhanced the accuracy of temporal information extraction…

In this paper, we propose an approach for Relationship Extraction (RE) based on labeled graph kernels. The kernel we propose is a particularization of a random walk kernel that exploits two properties previously studied in the RE…

Capsule Networks (CapsNets) have demonstrated to be a promising alternative to Convolutional Neural Networks (CNNs). However, they often fall short of state-of-the-art accuracies on large-scale high-dimensional datasets. We propose a…

Entity linking involves aligning textual mentions of named entities to their corresponding entries in a knowledge base. Entity linking systems often exploit relations between textual mentions in a document (e.g., coreference) to decide if…

Relation Extraction (RE) is one of the fundamental tasks in Information Extraction and Natural Language Processing. Dependency trees have been shown to be a very useful source of information for this task. The current deep learning models…

Attention mechanisms are often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention models are insufficient for the learning…

In this extended abstract, we present an algorithm that learns a similarity measure between documents from the network topology of a structured corpus. We leverage the Scaled Dot-Product Attention, a recently proposed attention mechanism,…

Recently, with the advances made in continuous representation of words (word embeddings) and deep neural architectures, many research works are published in the area of relation extraction and it is very difficult to keep track of so many…

In document-level relation extraction, entities may appear multiple times in a document, and their relationships can shift from one context to another. Accurate prediction of the relationship between two entities across an entire document…

Knowledge graphs are widely used as a typical resource to provide answers to factoid questions. In simple question answering over knowledge graphs, relation extraction aims to predict the relation of a factoid question from a set of…

Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic…