Related papers: Modelling Radiological Language with Bidirectional…

Recently, neural networks have achieved great success on sentiment classification due to their ability to alleviate feature engineering. However, one of the remaining challenges is to model long texts in document-level sentiment…

Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine learning problems that involve sequential data.…

In this work, we consider the medical concept normalization problem, i.e., the problem of mapping a disease mention in free-form text to a concept in a controlled vocabulary, usually to the standard thesaurus in the Unified Medical Language…

Recurrent neural networks (RNNs) have been applied to a broad range of applications, including natural language processing, drug discovery, and video recognition. Their vulnerability to input perturbation is also known. Aligning with a view…

With the increasing availability of patient data, modern medicine is shifting towards prospective healthcare. Electronic health records offer a variety of information useful for clinical patient characterization and the development of…

This paper argues that the judicial use of formal language theory and grammatical inference are invaluable tools in understanding how deep neural networks can and cannot represent and learn long-term dependencies in temporal sequences.…

Automated epileptic seizure detection from electroencephalogram (EEG) remains challenging due to significant individual differences in EEG patterns across patients. While existing studies achieve high accuracy with patient-specific…

Discourse segmentation, which segments texts into Elementary Discourse Units, is a fundamental step in discourse analysis. Previous discourse segmenters rely on complicated hand-crafted features and are not practical in actual use. In this…

Network evasion detection aims to distinguish whether the network flow comes from link layer exists network evasion threat, which is a means to disguise the data traffic on detection system by confusing the signature. Since the previous…

At the heart of radiological practice is the challenge of integrating complex imaging data with clinical information to produce actionable insights. Nuanced application of language is key for various activities, including managing requests,…

In medical information extraction, medical Named Entity Recognition (NER) is indispensable, playing a crucial role in developing medical knowledge graphs, enhancing medical question-answering systems, and analyzing electronic medical…

Relation classification is associated with many potential applications in the artificial intelligence area. Recent approaches usually leverage neural networks based on structure features such as syntactic or dependency features to solve…

We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the…

We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to…

The presence of bacteria or fungi in the bloodstream of patients is abnormal and can lead to life-threatening conditions. A computational model based on a bidirectional long short-term memory artificial neural network, is explored to assist…

Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised…

Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs incompatible with…

Detecting and intercepting malicious requests are one of the most widely used ways against attacks in the network security. Most existing detecting approaches, including matching blacklist characters and machine learning algorithms have all…

The advent of deep learning has considerably accelerated machine learning development. The deployment of deep neural networks at the edge is however limited by their high memory and energy consumption requirements. With new memory…

The current era of Natural Language Processing (NLP) is dominated by Transformer models. However, novel architectures relying on recurrent mechanisms, such as xLSTM and Mamba, have been proposed as alternatives to attention-based models.…