Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Explore this paper's citation graph

Summary

Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity is presented.

Type
article
Published
2019-08-14
Cited by
20,101
References
38
Access
Open access

Keywords

Sentence, Computer science, Artificial intelligence, Natural language processing

References

Cited by

Related papers