NLU-STR at SemEval-2024 Task 1: Generative-based Augmentation and Encoder-based Scoring for Semantic Textual Relatedness
Not on the map. Why?
Abstract (arXiv)
Semantic textual relatedness is a broader concept of semantic similarity. It measures the extent to which two chunks of text convey similar meaning or topics, or share related concepts or contexts. This notion of relatedness can be applied in various applications, such as document clustering and summarizing. SemRel-2024, a shared task in SemEval-2024, aims at reducing the gap in the semantic relatedness task by providing datasets for fourteen languages and dialects including Arabic. This paper reports on our participation in Track A (Algerian and Moroccan dialects) and Track B (Modern Standard Arabic). A BERT-based model is augmented and fine-tuned for regression scoring in supervised track (A), while BERT-based cosine similarity is employed for unsupervised track (B). Our system ranked 1st in SemRel-2024 for MSA with a Spearman correlation score of 0.49. We ranked 5th for Moroccan and 12th for Algerian with scores of 0.83 and 0.53, respectively.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 1 May 2024.
Builds on
27 of 50 references.
References · 27
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
- 2020Language-agnostic BERT Sentence Embeddingcited by 627
- 2020AraBERT: Transformer-based Model for Arabic Language Understandingcited by 362
- 2018Learning Word Vectors for 157 Languagescited by 280
- 2020ARBERT & MARBERT: Deep Bidirectional Transformers for Arabiccited by 166
- 2017Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotationcited by 79
- 2020A Panoramic Survey of Natural Language Processing in the Arab Worldcited by 45
- 2022Wojood: Nested Arabic Named Entity Corpus and Recognition using BERTcited by 33
15 more
- 2020A Comprehensive Survey on Word Representation Models: From Classical to State-Of-The-Art Word Representation Language Modelscited by 30
- 2022Curras + Baladi: Towards a Levantine Corpuscited by 20
- 2022The Arabic Ontology -- An Arabic Wordnet with Ontologically Clean Contentcited by 19
- 2022ArabGlossBERT: Fine-Tuning BERT on Context-Gloss Pairs for WSDcited by 18
- 2024SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languagescited by 16
- 2023Nabra: Syrian Arabic Dialects with Morphological Annotationscited by 11
- 2023A Benchmark and Scoring Algorithm for Enriching Arabic Synonymscited by 10
- 2023SALMA: Arabic Sense-Annotated Corpus and WSD Benchmarkscited by 10
- 2021LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguationcited by 9
- 2023ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabiccited by 8
- 2023Arabic Fine-Grained Entity Recognitioncited by 7
- 2023Context-Gloss Augmentation for Improving Arabic Target Sense Verificationcited by 6
- 2014Text Relatedness Based on a Word Thesauruscited by 2
- 2021Context-gloss Augmentation for Improving Word Sense Disambiguationcited by 2
- 2019Semantic Relatedness Based Re-ranker for Text Spottingcited by 1
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.