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

Document Expansion by Query Prediction #284

Open

chullhwan-song opened this issue Jan 13, 2020 · 1 comment

Labels

Bert neural ranking

Owner

chullhwan-song commented Jan 13, 2020

https://arxiv.org/abs/1904.08375

chullhwan-song added neural ranking Bert labels

chullhwan-song closed this as completed

Owner Author

chullhwan-song commented Jan 16, 2020 •

edited

Loading

Abstract

document에 대한 query를 예측하여 이를 trainset으로 사용하여 IR에 적용한다란게 이 논문의 요지
- doc2query > Query expansion
  - vanilla sequence-to-sequence model을 이용하여 query 예측 > https://github.com/nyu-dl/dl4ir-doc2query
이후 BERT 이용

SOTA

Introduction

Method: Doc2query

Doc2query
주어진 (query, relevant document) pair들로부터, "sequence-to-sequence transformer model" 이용하여, 입력 doc로 부터 query를 발생
BM25로 retrieval하고 BERT로 Re-Ranking
실제 BERT에 대한 자세한 사용방법은 없어서, 링크된 논문인 Passage Re-ranking with BERT #286 을 살펴봐야할듯하다.

실험

chullhwan-song reopened this

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