Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity

AbstractLearning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual STS: - (a): _cross-lingual transfer_ that exploits English resources alone as training data to yield non-English sentence embeddings as zero-shot inference, and - (b) _machine translation_ that coverts English data into pseudo non-English training data in advance. In our experiments on monolingual STS in Japanese and Korean, we find that the two data techniques yield performance on par. In addition, we find a superiority of Wikipedia domain over NLI domain as unlabeled training data for these languages. Combining our findings, we further demonstrate that the cross-lingual transfer of Wikipedia data exhibits improved performance.