Context-gloss augmentation for improving arabic target sense verification

S Malaysha, M Jarrar, M Khalilia - arxiv preprint arxiv:2302.03126, 2023 - arxiv.org
Arabic language lacks semantic datasets and sense inventories. The most common
semantically-labeled dataset for Arabic is the ArabGlossBERT, a relatively small dataset that …

NLU-STR at semeval-2024 task 1: Generative-based augmentation and encoder-based scoring for semantic textual relatedness

S Malaysha, M Jarrar, M Khalilia - arxiv preprint arxiv:2405.00659, 2024 - arxiv.org
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 …

[PDF][PDF] GPT-2 contextual data augmentation for word sense disambiguation

R Saidi, F Jarray, J Kang, D Schwab - Pacific Asia Conference on …, 2022 - hal.science
Abstract Most Word-Sense Disambiguation (WSD) systems rely on machine learning
approaches that require large-scale corpora for effective training. So, the quality of a WSD …

PoliTo at SemEval-2023 task 1: Clip-based visual-word sense disambiguation based on back-translation

L Vaiani, L Cagliero, P Garza - Proceedings of the 17th …, 2023 - aclanthology.org
Abstract Visual-Word Sense Disambiguation (V-WSD) entails resolving the linguistic
ambiguity in a text by selecting a clarifying image from a set of (potentially misleading) …