Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval

Yan Gao, Zhiwei Cao, Zhongjian Miao, Baosong Yang, Shiyu Liu, Min Zhang, Jinsong Su


Abstract
To achieve non-parametric NMT domain adaptation, k-Nearest-Neighbor Machine Translation (kNN-MT) constructs an external datastore to store domain-specific translation knowledge, which derives a kNN distribution to interpolate the prediction distribution of the NMT model via a linear interpolation coefficient πœ†. Despite its success, kNN retrieval at each timestep leads to substantial time overhead. To address this issue, dominant studies resort to kNN-MT with adaptive retrieval (kNN-MT-AR), which dynamically estimates πœ† and skips kNN retrieval if πœ† is less than a fixed threshold. Unfortunately, kNN-MT-AR does not yield satisfactory results. In this paper, we first conduct a preliminary study to reveal two key limitations of kNN-MT-AR: 1) the optimization gap leads to inaccurate estimation of πœ† for determining kNN retrieval skipping, and 2) using a fixed threshold fails to accommodate the dynamic demands for kNN retrieval at different timesteps. To mitigate these limitations, we then propose kNN-MT with dynamic retrieval (kNN-MT-DR) that significantly extends vanilla kNN-MT in two aspects. Firstly, we equip kNN-MT with a MLP-based classifier for determining whether to skip kNN retrieval at each timestep. Particularly, we explore several carefully-designed scalar features to fully exert the potential of the classifier. Secondly, we propose a timestep-aware threshold adjustment method to dynamically generate the threshold, which further improves the efficiency of our model. Experimental results on the widely-used datasets demonstrate the effectiveness and generality of our model.
Anthology ID:
2024.findings-acl.475
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7990–8001
Language:
URL:
https://aclanthology.org/2024.findings-acl.475
DOI:
10.18653/v1/2024.findings-acl.475
Bibkey:
Cite (ACL):
Yan Gao, Zhiwei Cao, Zhongjian Miao, Baosong Yang, Shiyu Liu, Min Zhang, and Jinsong Su. 2024. Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval. In Findings of the Association for Computational Linguistics ACL 2024, pages 7990–8001, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval (Gao et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.475.pdf