Dense Passage Retrieval for Open-Domain Question Answering: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
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 == | ||
= | = 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 == | ||
= | == 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.