AI NEWS.ccLaBSE
Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages. The pre-training process combines masked language modeling with translation language modeling. The model is useful for getting multilingual sentence embeddings and for bi-text retrieval. This is migrated from the v2 model on the TF Hub, which uses dict-based input. The embeddings produced by both the versions of the model are equivalent. Details about data, training, evaluation and performance metrics are available in the original paper.
翻訳準備中のため原文を表示しています
Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages. The pre-training process combines masked language modeling with translation language modeling. The model is useful for getting multilingual sentence embeddings and for bi-text retrieval. This is migrated from the v2 model on the TF Hub, which uses dict-based input. The embeddings produced by both the versions of the model are equivalent. Details about data, training, evaluation and performance metrics are available in the original paper.