TransAug: Translate as Augmentation for Sentence Embeddings. (arXiv:2111.00157v2 [cs.CL] UPDATED)

While contrastive learning greatly advances the representation of sentence
embeddings, it is still limited by the size of the existing sentence datasets.
In this paper, we present TransAug (Translate as Augmentation), which provide
the first exploration of utilizing translated sentence pairs as data
augmentation for text, and introduce a two-stage paradigm to advances the
state-of-the-art sentence embeddings. Instead of adopting an encoder trained in
other languages setting, we first distill a Chinese encoder from a SimCSE
encoder (pretrained in English), …

arxiv augmentation