DBLP-QuAD
DBLP-QuAD [1]</sup> is a KGQA dataset over DBLP KG, a scholarly knowledge graph. This dataset contains 10,000 question answer pairs with the corresponding SPARQL queries which can be executed over the DBLP KG to fetch the correct answer. DBLP-QuAD is the largest scholarly question answering dataset.
Leaderboard
| Model / System | Year | Exact Match (EM) | F1 Score | Language | Reported by |
|---|---|---|---|---|---|
| T5-base | 2023 | 72.1 | 86.8 | EN | Banerjee et al. |
| T5-small | 2023 | 63.8 | 81.3 | EN | Banerjee et al. |
References
[1] Banerjee, Debayan and Awale, Sushil and Usbeck, Ricardo and Biemann, Chris. DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph. In International Bibliometric Information Retrieval Workshp @ ECIR 2023.