New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

🚀 [2017] Reading Wikipedia to Answer Open-Domain Questions #25

Open

JudePark96 opened this issue Mar 23, 2021 · 2 comments

Assignees

Labels

arXiv NLP paper-reading

Owner

JudePark96 commented Mar 23, 2021

논문	Reading Wikipedia to Answer Open-Domain Questions
저자	Danqi Chen et al
링크	https://arxiv.org/pdf/1704.00051.pdf
학회	arXiv

Contents

1. 초록은 뭐라고 말하고 있어 ?

2. 주요 기여점은 뭐야 ?

3. 이전의 접근과는 뭐가 다른 것 같아 ?

4. 어떤 걸 제안할 수 있을까 ?

5. 다음 논문은 무엇을 읽어야할까 ?

JudePark96 added paper-reading NLP arXiv labels

JudePark96 self-assigned this

Owner Author

JudePark96 commented Mar 23, 2021

1. 초록은 뭐라고 말하고 있어 ?

접근 방식은 bigram hashing및 TF-IDF matching 을 기반으로하는 검색 구성 요소를 Wikipedia 단락에서 답변을 감지하도록 훈련 된 multi-layer recurrent neural network 모델과 결합합니다.

Owner Author

JudePark96 commented Mar 23, 2021

2. 주요 기여점은 뭐야 ?

Document Retriever
bigram hashing 과 TF-IDF matching 을 이용하여 relevant articles 을 효과적으로 가져올 수 있습니다.
Document Reader
relevant articles 로 multi-layer recurrent neural newtork 를 구성, machine reading comprehension 을 수행합니다.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment