Open Domain Question Answering On Natural
Metrics
Exact Match
Results
Performance results of various models on this benchmark
Model Name | Exact Match | Paper Title | Repository |
|---|---|---|---|
| R2-D2 w HN-DPR | 55.9 | R2-D2: A Modular Baseline for Open-Domain Question Answering | - |
| UniK-QA | 54.9 | UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering | - |
| UnitedQA (Hybrid) | 54.7 | UnitedQA: A Hybrid Approach for Open Domain Question Answering | - |
| BPR (linear scan; l=1000) | 41.6 | Efficient Passage Retrieval with Hashing for Open-domain Question Answering | - |
| FiE | 58.4 | 0.8% Nyquist computational ghost imaging via non-experimental deep learning | - |
0 of 5 row(s) selected.