We report the development of Japanese SimCSE, Japanese sentence embedding models fine-tuned with SimCSE. Since there is a lack of sentence embedding models for Japanese that can be used as a baseline in sentence embedding research, we conducted extensive experiments on Japanese sentence embeddings involving 24 pre-trained Japanese or multilingual language models, five supervised datasets, and four unsupervised datasets. In this report, we provide the detailed training setup for Japanese SimCSE and their evaluation results.
Cite
@article{arxiv.2310.19349,
title = {Japanese SimCSE Technical Report},
author = {Hayato Tsukagoshi and Ryohei Sasano and Koichi Takeda},
journal= {arXiv preprint arXiv:2310.19349},
year = {2023}
}