Related papers: A Robust Deep Ensemble Classifier for Figurative L…

This study investigates fine-tuning self-supervised learn ing (SSL) models using multi-task learning (MTL) to enhance speech emotion recognition (SER). The framework simultane ously handles four related tasks: emotion recognition, gender…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Decentralized learning (DL) is an emerging approach that enables nodes to collaboratively train a machine learning model without sharing raw data. In many application domains, such as healthcare, this approach faces challenges due to the…

Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications are stated and an interpretation function that translates…

SemEval-2019 Task 6 (Zampieri et al., 2019b) requires us to identify and categorise offensive language in social media. In this paper we will describe the process we took to tackle this challenge. Our process is heavily inspired by Sosa…

Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model's decision-making process. This necessitates not only an interpretable…

Foundational Language Models (FLMs) have advanced natural language processing (NLP) research. Current researchers are developing larger FLMs (e.g., XLNet, T5) to enable contextualized language representation, classification, and generation.…

Recognition of handwritten words continues to be an important problem in document analysis and recognition. Existing approaches extract hand-engineered features from word images--which can perform poorly with new data sets. Recently, deep…

Large language model hallucination represents a critical challenge where outputs deviate from factual accuracy due to distributional biases in training data. While recent investigations establish that specific hidden layers exhibit…

The spread of various forms of offensive speech online is an important concern in social media. While platforms have been investing heavily in ways of coping with this problem, the question of privacy remains largely unaddressed. Models…

Semantic representation and inference is essential for Natural Language Processing (NLP). The state of the art for semantic representation and inference is deep learning, and particularly Recurrent Neural Networks (RNNs), Convolutional…

This paper presents a novel end-to-end LLM-empowered explainable speech emotion recognition (SER) approach. Fine-grained speech emotion descriptor (SED) features, e.g., pitch, tone and emphasis, are disentangled from HuBERT SSL…

Deep Learning (DL) , a variant of the neural network algorithms originally proposed in the 1980s, has made surprising progress in Artificial Intelligence (AI), ranging from language translation, protein folding, autonomous cars, and more…

In recent years, several online platforms have seen a rapid increase in the number of review systems that request users to provide aspect-level feedback. Document-level Multi-aspect Sentiment Classification (DMSC), where the goal is to…

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…

Sarcasm detection, with its figurative nature, poses unique challenges for affective systems designed to perform sentiment analysis. While these systems typically perform well at identifying direct expressions of emotion, they struggle with…

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

We analyze the process of creating word embedding feature representations designed for a learning task when annotated data is scarce, for example, in depressive language detection from Tweets. We start with a rich word embedding pre-trained…

Background: Federated Learning (FL) has emerged as a promising paradigm for training machine learning models while preserving data privacy. However, applying FL to Natural Language Processing (NLP) tasks presents unique challenges due to…