· 2019
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- 11,192citations
- 2019year
Short summary
Sentence-BERT (SBERT) generates semantically meaningful sentence embeddings by fine-tuning BERT with a Siamese and triplet network structure, achieving state-of-the-art results on semantic textual similarity tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- Sentence-BERT (SBERT) fine-tunes BERT using Siamese and triplet networks to generate sentence embeddings.
- SBERT produces fixed-length sentence embeddings suitable for efficient clustering and comparison.
- The method achieves state-of-the-art performance on semantic textual similarity tasks.
- This approach significantly reduces computation time for similarity searches compared to standard BERT.
AI-generated from the title and abstract; the full text is not read.
Abstract
Nils Reimers, Iryna Gurevych. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
The authors' abstract, as published at the source., 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science