NLP

[BERT 논문 리뷰] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

코딩무민 2022. 3. 25. 14:33
반응형

1. Introduction

  • 2018년 10월 논문 공개
  • 당시, NLP 11개 task에 SOTA 달성
  • SQuAD v1.1에서 인간보다 더 높은 정확도를 보여 주목을 받음
  • 논문 제목 
    •  BERT: Pre-trainig of Deep Bidirectional Transformers for Language Understanding

논문 링크 

 

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations from unla

arxiv.org

설명 링크

https://coding-moomin.notion.site/BERT-f351597381d84e369bb429340593504b

 

BERT

content

coding-moomin.notion.site

 

반응형