Commit ·
9c5e5a3
1
Parent(s): 27bfefd
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
This model is DPR trained on MS MARCO. The training details and evaluation results are as follows:
|
| 6 |
+
|
| 7 |
+
|Model|Pretrain Model|Train w/ Marco Title|Marco Dev MRR@10|BEIR Avg NDCG@10|
|
| 8 |
+
|:----|:----|:----|:----|:----|
|
| 9 |
+
|DPR|bert-base-uncased|w/|32.4|35.5|
|
| 10 |
+
|
| 11 |
+
|BERI Dataset|NDCG@10|
|
| 12 |
+
|:----|:----|
|
| 13 |
+
|TREC-COVID|58.8|
|
| 14 |
+
|NFCorpus|0.234|
|
| 15 |
+
|FiQA|0.206|
|
| 16 |
+
|ArguAna|0.394|
|
| 17 |
+
|Touché-2020|0.223|
|
| 18 |
+
|Quora|0.780|
|
| 19 |
+
|SCIDOCS|0.119|
|
| 20 |
+
|SciFact|0.494|
|
| 21 |
+
|NQ|0.439|
|
| 22 |
+
|HotpotQA|0.453|
|
| 23 |
+
|Signal-1M|0.202|
|
| 24 |
+
|TREC-NEWS|0.318|
|
| 25 |
+
|DBPedia-entity|0.287|
|
| 26 |
+
|Fever|0.650|
|
| 27 |
+
|Climate-Fever|0.149|
|
| 28 |
+
|BioASQ|0.241|
|
| 29 |
+
|Robust04|0.323|
|
| 30 |
+
|CQADupStack|0.283|
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
The implementation is the same as our EMNLP 2022 paper ["Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives"](https://arxiv.org/pdf/2210.17167.pdf). The associated GitHub repository is available at https://github.com/OpenMatch/ANCE-Tele.
|
| 34 |
+
|
| 35 |
+
```
|
| 36 |
+
@inproceedings{sun2022ancetele,
|
| 37 |
+
title={Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives},
|
| 38 |
+
author={Si, Sun and Chenyan, Xiong and Yue, Yu and Arnold, Overwijk and Zhiyuan, Liu and Jie, Bao},
|
| 39 |
+
booktitle={Proceedings of EMNLP 2022},
|
| 40 |
+
year={2022}
|
| 41 |
+
}
|
| 42 |
+
```
|