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. 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 and skips kNN retrieval if π 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 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:
- 7990β8001
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.475
- DOI:
- 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 7990β8001, 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.475.pdf