Difference between revisions of "Dense Passage Retrieval for Open-Domain Question Answering"

From statwiki
Jump to: navigation, search
Line 2: Line 2:
 
Nicole Yan
 
Nicole Yan
  
= Introduction =
+
= 1. Introduction =
  
  
= Background =
+
= 2. Background =
  
  
= Dense Passage Retriever =
+
= 3. Dense Passage Retriever =
  
== Model Architecture Overview ==
+
== 3.1 Model Architecture Overview ==
  
== Training ==
+
== 3.2 Training ==
  
= Datasets =
+
= 4. Experimental Setup =
  
= Retrieval Performance Evaluation =
+
= 5. Retrieval Performance Evaluation =
  
== Main Results ==
+
== 5.1 Main Results ==
  
== Ablation Study on Model Training ==
+
== 5.2 Ablation Study on Model Training ==
  
= Experiments: Question Answering =
+
== 5.3 Qualitative Analysis ==
  
= Conclusion =
+
== 5.4 Run-time Efficiency ==
 +
 
 +
= 6. Experiments: Question Answering =
 +
 
 +
= 7. Related Work =
 +
 
 +
= 8. Conclusion =
  
 
= Critiques =
 
= Critiques =

Revision as of 00:25, 14 November 2020

Presented by

Nicole Yan

1. Introduction

2. Background

3. Dense Passage Retriever

3.1 Model Architecture Overview

3.2 Training

4. Experimental Setup

5. Retrieval Performance Evaluation

5.1 Main Results

5.2 Ablation Study on Model Training

5.3 Qualitative Analysis

5.4 Run-time Efficiency

6. Experiments: Question Answering

7. Related Work

8. 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.