Description
The Deep Learning track focuses on IR tasks where a large training set is available, allowing us to compare a variety of retrieval approaches including deep neural networks and strong non-neural approaches, to see what works best in a large-data regime.
Resources
| Name | Format | Description | Link |
|---|---|---|---|
| Document Ranking Corpus | Unknown | Open resource | |
| Document Ranking Corpus | Unknown | Open resource | |
| Passage Ranking Topics | Unknown | Open resource | |
| Passage Ranking Corpus | Unknown | Open resource | |
| Passage Ranking Topics | Unknown | Open resource | |
| 2023 Deep Learning Data Page | HTML | deep2023.html | Open resource |
| Document Ranking (NIST, 1 judgments mapped to 0) | Text | 2023.qrels.docs.wihDupes.no1.txt | Open resource |
| Document Ranking NIST QRels | Text | 2023.qrels.docs.wihDupes.txt | Open resource |
| Passage Ranking (NIST, 1 judgments mapped to 0) | Text | 2023.qrels.pass.withDupes.no1.txt | Open resource |
| Passage Ranking NIST QRels | Text | 2023.qrels.pass.withDupes.txt | Open resource |