MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness
Domain:
natural language processingRecord type:
paper
Creator:
ZhoShaPlaLit
Host:
This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. The task aims to detect semantic relatedness of two sentences in a given target language without access to direct supervision (i.e. zero-shot cross-lingual transfer). To this end, we focus on different source language selection strategies on two different pre-trained languages models: XLM-R and Furina. We experiment with 1) single-source transfer and select source languages based on typological similarity, 2) augmenting English training data with the two nearest-neighbor source languages, and 3) multi-source transfer where we compare selecting on all training languages against languages from the same family. We further study machine translation-based data augmentation and the impact of script differences. Our submission achieved the first place in the C8 (Kinyarwanda) test set.
Similar
WarwickNLP at SemEval-2024 Task 1: Low-Rank Cross-Encoders for Efficient Semantic Textual RelatednessMasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual RelatednessAAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual RelatednessHausaNLP at SemEval-2024 Task 1: Textual Relatedness Analysis for Semantic Representation of SentencesSemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian LanguagesIITK at SemEval-2024 Task 1: Contrastive Learning and Autoencoders for Semantic Textual Relatedness in Multilingual Texts