Nonparametric Decoding for Generative Retrieval

Hyunji Lee, JaeYoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vladimir Karpukhin, Yi Lu, Minjoon Seo


Abstract
The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametric Decoding (Np Decoding) which can be applied to existing generative retrieval models. Np Decoding uses nonparametric contextualized vocab embeddings (external memory) rather than vanilla vocab embeddings as decoder vocab embeddings. By leveraging the contextualized vocab embeddings, the generative retrieval model is able to utilize both the parametric and nonparametric space. Evaluation over 9 datasets (8 single-hop and 1 multi-hop) in the document retrieval task shows that applying Np Decoding to generative retrieval models significantly improves the performance. We also show that Np Decoding is data- and parameter-efficient, and shows high performance in the zero-shot setting.
Anthology ID:
2023.findings-acl.801
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:
12642–12661
Language:
URL:
https://aclanthology.org/2023.findings-acl.801
DOI:
10.18653/v1/2023.findings-acl.801
Bibkey:
Cite (ACL):
Hyunji Lee, JaeYoung Kim, Hoyeon Chang, Hanseok Oh, Sohee Yang, Vladimir Karpukhin, Yi Lu, and Minjoon Seo. 2023. Nonparametric Decoding for Generative Retrieval. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12642–12661, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Nonparametric Decoding for Generative Retrieval (Lee et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.801.pdf