Zhirui Zhang, Yuhan Dai, Qiuzhi Liu, Qu Cui, Weihua Li, Yichao Du, Tong Xu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
kNN- MT (Khandelwal et al., 2021) is a straightforward yet powerful approach for fast domain adaptation, which directly plugs pre-trained neural machine translation (NMT) models with domain-specific token-level k-nearest-neighbor (kNN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, kNN-MT is burdened with massive storage requirements and high computational complexity since it conducts nearest neighbor searches over the entire reference corpus. In this paper, we propose a simple and scalable nearest neighbor machine translation framework to drastically promote the decoding and storage efficiency of kNN-based models while maintaining the translation performance. To this end, we dynamically construct an extremely small datastore for each input via sentence-level retrieval to avoid searching the entire datastore in vanilla kNN-MT, based on which we further introduce a distance-aware adapter to adaptively incorporate the kNN retrieval results into the pre-trained NMT models. Experiments on machine translation in two general settings, static domain adaptation, and online learning, demonstrate that our proposed approach not only achieves almost 90% speed as the NMT model without performance degradation, but also significantly reduces the storage requirements of kNN-MT.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.12188")
get_code_for_paper("2302.12188")
have("2302.12188")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.12188.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.12188)
Connect an agent — have() is free.