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.
Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison
1 Pith paper cite this work. Polarity classification is still indexing.
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.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
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.