Dynamic Batch Sizing Strategies in Label-Aware Multi-Level Contrastive Learning for Zero-Shot Cross-Lingual Tasks

Cross-language pre-trained models such as multilingual BERT (mBERT) have achieved significant performance in various cross-lingual downstream NLP tasks. This paper proposes a multi-level contrastive learning (ML-CTL) framework to further improve the cross-lingual ability of pre-trained models. The proposed method uses translated parallel data to encourage the model to generate similar semantic embeddings for different languages. However, unlike the sentence-level alignment used in most previous studies, in this paper, we explicitly integrate the word-level information of each pair of parallel

Research goal: How does the incorporation of dynamic batch sizing strategies impact the trade-off between computational efficiency and performance in label-aware multi-level contrastive learning for zero-shot cross-lingual tasks, as measured by F1 scores on the XTREME-R benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.