Pith. sign in

REVIEW 4 cited by

Nearest Neighbor Machine Translation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.00710 v2 pith:Q76FOAST submitted 2020-10-01 cs.CL

Urvashi Khandelwal , Angela Fan , Dan Jurafsky , Luke Zettlemoyer , Mike Lewis This is my paper
classification cs.CL
keywords modeltranslationbleuexamplesnearestneighbornn-mtdatastore
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We introduce $k$-nearest-neighbor machine translation ($k$NN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. This approach requires no additional training and scales to give the decoder direct access to billions of examples at test time, resulting in a highly expressive model that consistently improves performance across many settings. Simply adding nearest neighbor search improves a state-of-the-art German-English translation model by 1.5 BLEU. $k$NN-MT allows a single model to be adapted to diverse domains by using a domain-specific datastore, improving results by an average of 9.2 BLEU over zero-shot transfer, and achieving new state-of-the-art results -- without training on these domains. A massively multilingual model can also be specialized for particular language pairs, with improvements of 3 BLEU for translating from English into German and Chinese. Qualitatively, $k$NN-MT is easily interpretable; it combines source and target context to retrieve highly relevant examples.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability

    cs.CL 2025-02 unverdicted novelty 7.0 of 10

    ExaGPT uses span-level similarity retrieval from human and LLM datastores to detect machine-generated text while supplying the matching spans as human-interpretable evidence, achieving up to 37-point accuracy gains ov...

  2. Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    BadRDM is a backdoor attack on retrieval-augmented diffusion models that poisons the retrieval database with toxicity surrogates and uses multimodal contrastive learning to force toxic generations from text triggers w...

  3. Retrieval-Augmented Generation for Natural Language Processing: A Survey

    cs.CL 2024-07 accept novelty 6.0 of 10

    The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.

  4. Worlds Within Words: Translating Culture in Ancient Chinese Texts with Multi-Agent Coordination

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    MACAT is a multi-agent culture-aware translation system that dynamically explicates culture-loaded words in ancient Chinese texts and outperforms baselines on TCM classics and Analects under GPT-5.4 evaluation.

Pith tools