Pith. sign in

REVIEW 1 cited by

Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison

Not yet reviewed by Pith; the record is open.

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 2404.02835 v1 pith:2LBJCKBL submitted 2024-04-03 cs.CL

classification cs.CL
keywords architecturesexamplesretrievaltranslationmodelacrossexperimentslanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-Augmented Neural Machine Translation (RAMT) architectures retrieve examples from memory to guide the generation process. While most works in this trend explore new ways to exploit the retrieved examples, the upstream retrieval step is mostly unexplored. In this paper, we study the effect of varying retrieval methods for several translation architectures, to better understand the interplay between these two processes. We conduct experiments in two language pairs in a multi-domain setting and consider several downstream architectures based on a standard autoregressive model, an edit-based model, and a large language model with in-context learning. Our experiments show that the choice of the retrieval technique impacts the translation scores, with variance across architectures. We also discuss the effects of increasing the number and diversity of examples, which are mostly positive across the board.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning

    cs.AI 2025-07 conditional novelty 4.0 of 10

    A multimodal, memory-augmented multi-agent system for video subtitling and translation, plus a new 17-hour benchmark, reports large BLEU/SubER gains on its own benchmark but not consistently on existing benchmarks.

Pith tools