Related papers: Boosting Span-based Joint Entity and Relation Extr…

Recent studies indicate that Vision Transformers (ViTs) are robust against out-of-distribution scenarios. In particular, the Fully Attentional Network (FAN) - a family of ViT backbones, has achieved state-of-the-art robustness. In this…

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However,…

In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context (negative instances) usually far…

Named Entity Recognition (NER) is the task of identifying spans that represent entities in sentences. Whether the entity spans are nested or discontinuous, the NER task can be categorized into the flat NER, nested NER, and discontinuous NER…

Extracting structured information from scientific literature is critical for accelerating discovery, yet Large Language Models (LLMs) often struggle in specialized domains that require expert knowledge and generalize poorly across tasks. We…

Graph Neural Networks (GNNs) have superior capability in learning graph data. Full-graph GNN training generally has high accuracy, however, it suffers from large peak memory usage and encounters the Out-of-Memory problem when handling large…

Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that…

Many approaches to transform classification problems from non-linear to linear by feature transformation have been recently presented in the literature. These notably include sparse coding methods and deep neural networks. However, many of…

In the field of deep learning, Graph Neural Networks (GNNs) and Graph Transformer models, with their outstanding performance and flexible architectural designs, have become leading technologies for processing structured data, especially…

Steganalysis has been an important research topic in cybersecurity that helps to identify covert attacks in public network. With the rapid development of natural language processing technology in the past two years, coverless steganography…

Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-texture, occlusions and reflections. Concurrently, deep…

Open relation extraction (ORE) remains a challenge to obtain a semantic representation by discovering arbitrary relation tuples from the unstructured text. Conventional methods heavily depend on feature engineering or syntactic parsing,…

Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest, owing to the transformer's exceptional capacity to capture long-range pixel dependencies. Nevertheless, current RGB-D SOD methods face…

The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network…

Sequence generation demonstrates promising performance in recent information extraction efforts, by incorporating large-scale pre-trained Seq2Seq models. This paper investigates the merits of employing sequence generation in relation…

Detection and disambiguation of all entities in text is a crucial task for a wide range of applications. The typical formulation of the problem involves two stages: detect mention boundaries and link all mentions to a knowledge base. For a…

Text-to-image person re-identification (ReID) aims to search for images containing a person of interest using textual descriptions. However, due to the significant modality gap and the large intra-class variance in textual descriptions,…

Inter-sentence relation extraction deals with a number of complex semantic relationships in documents, which require local, non-local, syntactic and semantic dependencies. Existing methods do not fully exploit such dependencies. We present…

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…

One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages. In this work, we investigate the robustness of the mention detection systems, one of the fundamental tasks…