2022/05/24 by Pedro Henrique Martins, Martins, Pedro Henrique, Zita Marinho +3 · 1 citation
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2205.12230
Semi-parametric models, which augment generation with retrieval, have led to impressive results in language modeling and machine translation, due to their ability to retrieve fine-grained information from a datastore of examples. One of the most prominent approaches, kNN-MT, exhibits strong domain adaptation capabilities by retrieving tokens from domain-specific datastores \citepkhandelwal2020nearest. However, kNN-MT requires an expensive retrieval operation for every single generated token, leading to a very low decoding speed (around 8 times slower than a parametric model). In this paper, we introduce a chunk-based kNN-MT model which retrieves chunks of tokens from the datastore, instead of a single token. We propose several strategies for incorporating the retrieved chunks into the generation process, and for selecting the steps at which the model needs to search for neighbors in the datastore. Experiments on machine translation in two settings, static and ``on-the-fly'' domain adaptation, show that the chunk-based kNN-MT model leads to significant speed-ups (up to 4 times) with only a small drop in translation quality.