Dense Passage Retrieval for Open-Domain Question Answering

From statwiki
Revision as of 23:21, 13 November 2020 by X46yan (talk | contribs)
Jump to: navigation, search

Presented by

Nicole Yan

Introduction

Background

Dense Passage Retriever

Model Architecture Overview

Training

Datasets

Retrieval Performance Evaluation

Main Results

Ablation Study on Model Training

Experiments: Question Answering

Conclusion

Critiques

References

[1] Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih. Dense Passage Retrieval for Open-Domain Question Answering. EMNLP 2020.