SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives

Fedor Moiseev, Gustavo Hernandez Abrego, Peter Dornbach, Imed Zitouni, Enrique Alfonseca, Zhe Dong


Abstract
Dual encoders have been used for retrieval tasks and representation learning with good results. A standard way to train dual encoders is using a contrastive loss with in-batch negatives. In this work, we propose an improved contrastive learning objective by adding queries or documents from the same encoder towers to the negatives, for which we name it as “contrastive loss with SAMe TOwer NEgatives” (SamToNe). By evaluating on question answering retrieval benchmarks from MS MARCO and MultiReQA, and heterogenous zero-shot information retrieval benchmarks (BEIR), we demonstrate that SamToNe can effectively improve the retrieval quality for both symmetric and asymmetric dual encoders. By directly probing the embedding spaces of the two encoding towers via the t-SNE algorithm (van der Maaten and Hinton, 2008), we observe that SamToNe ensures the alignment between the embedding spaces from the two encoder towers. Based on the analysis of the embedding distance distributions of the top-1 retrieved results, we further explain the efficacy of the method from the perspective of regularisation.
Anthology ID:
2023.findings-acl.761
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12028–12037
Language:
URL:
https://aclanthology.org/2023.findings-acl.761
DOI:
10.18653/v1/2023.findings-acl.761
Bibkey:
Cite (ACL):
Fedor Moiseev, Gustavo Hernandez Abrego, Peter Dornbach, Imed Zitouni, Enrique Alfonseca, and Zhe Dong. 2023. SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12028–12037, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives (Moiseev et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2023.findings-acl.761.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-1/2023.findings-acl.761.mp4