Related papers: BrightCookies at SemEval-2025 Task 9: Exploring Da…

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Safety for Large Language Models (LLMs) has been an ongoing research focus since their emergence and is even more relevant nowadays with the increasing capacity of those models. Currently, there are several guardrails in place for all…

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model…

This paper presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. For the individual models, deep transformer…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…

This paper describes our participation in SemEval-2023 Task 9, Intimacy Analysis of Multilingual Tweets. We fine-tune some of the most popular transformer models with the training dataset and synthetic data generated by different data…

The widespread popularity of social media has led to an increase in hateful, abusive, and sexist language, motivating methods for the automatic detection of such phenomena. The goal of the SemEval shared task \textit{Towards Explainable…

Subjectivity and difference of opinion are key social phenomena, and it is crucial to take these into account in the annotation and detection process of derogatory textual content. In this paper, we use four datasets provided by…

Graph classification, which aims to identify the category labels of graphs, plays a significant role in drug classification, toxicity detection, protein analysis etc. However, the limitation of scale of benchmark datasets makes it easy for…

Large datasets' availability is catalyzing a rapid expansion of deep learning in general and computer vision in particular. At the same time, in many domains, a sufficient amount of training data is lacking, which may become an obstacle to…

Text classification tasks often encounter few shot scenarios with limited labeled data, and addressing data scarcity is crucial. Data augmentation with mixup has shown to be effective on various text classification tasks. However, most of…

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve…

Type- and token-based embedding architectures are still competing in lexical semantic change detection. The recent success of type-based models in SemEval-2020 Task 1 has raised the question why the success of token-based models on a…

Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation -- a technique…

Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a…

This paper describes our participation in the DEtection of TOXicity in comments In Spanish (DETOXIS) shared task 2021 at the 3rd Workshop on Iberian Languages Evaluation Forum. The shared task is divided into two related classification…

This paper presents AI Wizards' participation in the CLEF 2025 CheckThat! Lab Task 1: Subjectivity Detection in News Articles, classifying sentences as subjective/objective in monolingual, multilingual, and zero-shot settings.…