NLP

[SBERT 논문리뷰] Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

코딩무민 2022. 5. 24. 17:12
반응형

1. 핵심 요약 

  • BERT의 문제점
    • STS task에서 문장이 같은 네트워크에 들어가기 때문에 massive computational overhead 발생
    • → BERT : Semantic Search나 unsupervised tasks에 적합하지 않음
  • Sentence-BERT(SBERT)
    • siamese and triplet network 구조를 활용한 pre-trained BERT 네트워크
    • 가장 비슷한 similar pairs를 찾는 시간을 시간을 65 hours에서 약 5초로 단축 & accuarcy는 유지
    • sentence embedding methods에서 SOTA outperform

2. 논문 링크

https://arxiv.org/abs/1908.10084

 

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes a

arxiv.org

3. 논문 설명 링크 

https://coding-moomin.notion.site/Sentence-BERT-Sentence-Embeddings-using-Siamese-BERT-Networks-b40895a091ed45cfa837a4f163a16bc1

 

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

content

coding-moomin.notion.site

 

반응형