Articles

AbstractUsing pre-trained language models to implement classifiers from small to modest amounts of training data is an area of active research. The ability of large language models to generalize from few-shot examples and to produce strong classifiers is extended using the engineering approach of parameter-efficient tuning. Using the Explainable Detection …...

AbstractThis paper elaborates on our work in designing a system for SemEval 2023 Task 12: AfriSentiSemEval, which involves sentiment analysis for low-resource African languages using the Twitter dataset. We utilised a pre-trained model to perform sentiment classification in Hausa language tweets. We used a multilingual version of the roBERTa model, …...

AbstractThis paper describes our submission to Task 10 at SemEval 2023-Explainable Detection of Online Sexism (EDOS), divided into three subtasks. The recent rise in social media platforms has seen an increase in disproportionate levels of sexism experienced by women on social media platforms. This has made detecting and explaining online …...

AbstractThis report describes GMU’s sentiment analysis system for the SemEval-2023 shared task AfriSenti-SemEval. We participated in all three sub-tasks: Monolingual, Multilingual, and Zero-Shot. Our approach uses models initialized with AfroXLMR-large, a pre-trained multilingual language model trained on African languages and fine-tuned correspondingly. We also introduce augmented training data along with …...

AbstractThis paper describes our approach for Subtask 1 of Task 3 at SemEval-2023. In this subtask, task participants were asked to classify multilingual news articles for one of three classes: Reporting, Opinion Piece or Satire. By training an AdapterFusion layer composing the task-adapters from different languages, we successfully combine the …...

AbstractIn this paper, we have performed sentiment analysis on three African languages (Hausa, Swahili, and Yoruba). We used various deep learning and traditional models paired with a vectorizer for classification and data -preprocessing. We have also used a few data oversampling methods to handle the imbalanced text data. Thus, we …...

AbstractThe MultiCoNER II shared task aims at detecting complex, ambiguous named entities with fine-grained types in a low context setting. Previous winning systems incorporated external knowledge bases to retrieve helpful contexts. In our submission we additionally propose splitting the NER task into two stages, a Span Extraction Step, and an …...

AbstractWe present our submission to SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS). We address all three tasks: Task A consists of identifying whether a post is sexist. If so, Task B attempts to assign it one of four categories: threats, derogation, animosity, and prejudiced discussions. Task C aims …...

AbstractThe ability to automatically recognise the rhetorical roles of sentences in a legal case judgement is a crucial challenge to tackle since it can be useful for a number of activities that come later, such as summarising legal judgements and doing legal searches. The task is exigent since legal case …...

AbstractThis paper describes the submission to SemEval-2023 Task 2: Multilingual Complex Named Entity Recognition (MultiCoNER II) by team SAB. This task aims to encourage growth in the field of Named Entity Recognition (NER) by focusing on complex and difficult categories of entities, in 12 different language tracks. The task of …...

AbstractOur team silp_nlp participated in SemEval2023 Task 2: MultiCoNER II. Our work made systems for 11 mono-lingual tracks. For leveraging the advantage of all track knowledge we chose transformer-based pretrained models, which have strong cross-lingual transferability. Hence our model trained in two stages, the first stage for multi-lingual learning from …...

AbstractWithin the scope of the shared task MultiCoNER II our aim was to improve the recognition of named entities in English. We as team Minanto fine-tuned a cross-lingual model for Named Entity Recognition on English data and achieved an average F1 score of 51.47\% in the final submission. We found …...

AbstractRhetorical Roles (RR) prediction is to predict the label of each sentence in legal documents, which is regarded as an emergent task for legal document understanding. In this study, we present a novel method for the RR task by exploiting the long context representation. Specifically, legal documents are known as …...

AbstractSocial media is the media through which people share their thoughts and opinions. This has both its pros and cons which depends on the type of information being conveyed. If any information conveyed over social media hurts or affects a person, such information can be removed as it may disturb …...

AbstractIn this paper, I describe the approach used in the SemEval 2023 - Task 10 Explainable Detection of Online Sexism (EDOS) competition (Kirk et al., 2023). I use different transformermodels, including BERT and RoBERTa which were fine-tuned on the EDOS dataset to classify text into different categories of sexism. I …...

AbstractThis task focuses on identifying complex named entities (NEs) in several languages. In the context of SemEval-2023 competition, our team presents an exploration of a base transformer model’s capabilities regarding the task, focused more specifically on five languages (English, Spanish, Swedish, German, Italian). We take DistilBERT and BERT as two …...

AbstractSystem Description Paper for Task 3 Subtask 1 and 2 of Semeval 2023. The paper describes our approach to handling the News Genre Categorisation and Framing Detection using RoBERTa and ALBERT models....

AbstractThis paper describes the development of a system for SemEval-2023 Shared Task 11 on Learning with Disagreements (Le-Wi-Di). Labelled data plays a vital role in the development of machine learning systems. The human-annotated labels are usually considered the truth for training or validation. To obtain truth labels, a traditional way …...

AbstractAs social media platforms grow, so too does the volume of hate speech and negative sentiment expressed towards particular social groups. In this paper, we describe our approach to SemEval-2023 Task 10, involving the detection and classification of online sexism (abuse directed towards women), with fine-grained categorisations intended to facilitate …...

AbstractThe Clickbait Spoiling shared task aims at tackling two aspects of spoiling: classifying the spoiler type based on its length and generating the spoiler. This paper focuses on the task of classifying the spoiler type. Better classification of the spoiler type would eventually help in generating a better spoiler for …...