SemEval-2024 Task 1: MasonTigers Ensemble Approach for Semantic Textual Relatedness
MasonTigers presented an ensemble approach for Semantic Textual Relatedness at SemEval-2024, achieving notable rankings across different languages and tracks.
Semantic Textual Relatedness: A Multilingual Shared Task Covering 14 Languages Across Africa and Asia
This shared task investigates the broader phenomenon of semantic textual relatedness across 14 languages, including low-resource languages from Africa and Asia, and provides datasets, baselines, and evaluation of participating systems.
SemEval-2024 Task 1: MasonTigers' Ensemble Approach for Multilingual Semantic Textual Relatedness
MasonTigers utilized an ensemble approach combining statistical machine learning techniques and language-specific BERT models to achieve strong performance across supervised, unsupervised, and cross-lingual tracks of the SemEval-2024 Task 1 on Semantic Textual Relatedness.
Multilingual Semantic Textual Relatedness: Augmentation and Adaptation for Improved Performance
Our system AAdaM achieves competitive results in the SemEval-2024 Task 1 on Semantic Textual Relatedness for African and Asian languages, by leveraging data augmentation, task-adaptive pre-training, and adapter-based tuning.
Self-StrAE: Improving Hierarchical Representation Learning with Fewer Parameters
Two simple improvements to the Self-Structuring AutoEncoder (Self-StrAE) model lead to significant performance gains in capturing semantic relatedness, while simultaneously reducing the number of model parameters.
IITK's Multilingual Semantic Textual Relatedness System for SemEval-2024 Task 1
The paper presents a system developed by IITK for the SemEval-2024 Task 1: Semantic Textual Relatedness, which focuses on automatically detecting the degree of relatedness between pairs of sentences in 14 languages, including both high and low-resource Asian and African languages. The system utilizes a BERT-based contrastive learning approach and similarity metric-based approach for the supervised track, as well as transformer autoencoders for the unsupervised track.
UMBCLU's Semantic Textual Relatedness Models for African and Asian Languages with and without Machine Translation
The authors developed two models, TranSem and FineSem, to identify semantic textual relatedness between sentence pairs in 14 African and Asian languages, exploring the effectiveness of machine translation and different training strategies.
Generative-based Augmentation and Encoder-based Scoring for Semantic Textual Relatedness in Arabic Dialects and Modern Standard Arabic
Our system employs supervised and unsupervised techniques using BERT-based language models to achieve competitive performance on the SemEval-2024 Task 1 for semantic textual relatedness in Arabic dialects and Modern Standard Arabic.
