mlsanityData to 7 Oct 2026

MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness

arXiv 2404.02570 ↗First posted 3 Apr 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

16 of 26 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  5. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  6. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  7. 2020XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generationcited by 221
  8. 2023Glot500: Scaling Multilingual Corpora and Language Models to 500 Languagescited by 116
  9. 2021Revisiting the Primacy of English in Zero-shot Cross-lingual Transfercited by 47
  10. 2017Learning Language Representations for Typology Predictioncited by 40
  11. 2023XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languagescited by 34
  12. 2022A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bankcited by 29
4 more
  1. 2016Continuous multilinguality with language vectorscited by 20
  2. 2024SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languagescited by 16
  3. 2023Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroesecited by 15
  4. 2024Analysis of Multi-Source Language Training in Cross-Lingual Transfercited by 5

Built on by

Not cited yet.