Downloads · 30 days
11
3% of all-time downloads
ance-tele_nq_qry-encoder
OpenMatch/ance-tele_nq_qry-encoder
ance-tele_nq_qry-encoder is a feature extraction model from OpenMatch. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as mit.
This model is the query encoder of ANCE-Tele trained on NQ, described in the EMNLP 2022 paper "Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives". The associated GitHub repository…
All-time downloads
375
Public
Repo size
876 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Oct 30, 2022
- Updated
- Mar 20, 2023
- SHA
- 0b2fdbc8
Model card
From the Hugging Face model README
This model is the query encoder of ANCE-Tele trained on NQ, described in the EMNLP 2022 paper "Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives". The associated GitHub repository is available at https://github.com/OpenMatch/ANCE-Tele.
ANCE-Tele only trains with self-mined negatives (teleportation negatives) without using additional negatives (e.g., BM25, other DR systems) and eliminates the dependency on filtering strategies and distillation modules.
| NQ (Test) | R@5 | R@20 | R@20 |
|---|---|---|---|
| ANCE-Tele | 77.0 | 84.9 | 89.7 |
@inproceedings{sun2022ancetele,
title={Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives},
author={Si, Sun and Chenyan, Xiong and Yue, Yu and Arnold, Overwijk and Zhiyuan, Liu and Jie, Bao},
booktitle={Proceedings of EMNLP 2022},
year={2022}
}
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Oct 30, 2022
- Updated
- Mar 20, 2023