Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityIn-Context LearningLanguage ModelingLanguage ModellingLarge Language ModelMachine TranslationRetrievalTranslationSimilar Papers 제목 키워드 기반
Optimizing example selection for retrieval-augmented machine translation with translation memories
Retrieval-augmented machine translation leverages examples from a translation memory by retrieving similar instances. These examples are used to condition the predictions of a neural decoder. We aim to improve the upstre…
DecoderMachine TranslationRetrievalSentence+1Improving Image Recognition by Retrieving from Web-Scale Image-Text Data
Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar ex…
Image ClassificationLearning with noisy labelsLong-tail LearningRetro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization
The retrieval augmented generation (RAG) system such as Retro has been shown to improve language modeling capabilities and reduce toxicity and hallucinations by retrieving from a database of non-parametric memory contain…
Language ModelingLanguage ModellingRAGRetrieval+3Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
Maintaining long-term geometric consistency remains challenging for long-horizon autoregressive video generation. Memory-augmented generative models address this by retrieving historical frames, but their effectiveness d…
3D ReconstructionVideo GenerationEnhancing E-commerce Product Title Translation with Retrieval-Augmented Generation and Large Language Models
E-commerce stores enable multilingual product discovery which require accurate product title translation. Multilingual large language models (LLMs) have shown promising capacity to perform machine translation tasks, and …
Machine TranslationRAGRetrievalRetrieval-augmented Generation+1