Efficient Machine Translation Domain Adaptation

04/26/2022
by   Pedro Henrique Martins, et al.
1

Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model on every new domain, which can be costly. On the other hand, semi-parametric models have been shown to successfully perform domain adaptation by retrieving examples from an in-domain datastore (Khandelwal et al., 2021). A drawback of these retrieval-augmented models, however, is that they tend to be substantially slower. In this paper, we explore several approaches to speed up nearest neighbor machine translation. We adapt the methods recently proposed by He et al. (2021) for language modeling, and introduce a simple but effective caching strategy that avoids performing retrieval when similar contexts have been seen before. Translation quality and runtimes for several domains show the effectiveness of the proposed solutions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/24/2022

Chunk-based Nearest Neighbor Machine Translation

Semi-parametric models, which augment generation with retrieval, have le...
research
09/15/2023

Neural Machine Translation Models Can Learn to be Few-shot Learners

The emergent ability of Large Language Models to use a small number of e...
research
06/16/2021

Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation

Policy gradient algorithms have found wide adoption in NLP, but have rec...
research
04/05/2018

Domain Adaptation for Statistical Machine Translation

Statistical machine translation (SMT) systems perform poorly when it is ...
research
11/15/2022

Adaptation Approaches for Nearest Neighbor Language Models

Semi-parametric Nearest Neighbor Language Models (kNN-LMs) have produced...
research
05/27/2020

MT-Adapted Datasheets for Datasets: Template and Repository

In this report we are taking the standardized model proposed by Gebru et...
research
10/05/2016

Neural Structural Correspondence Learning for Domain Adaptation

Domain adaptation, adapting models from domains rich in labeled training...

Please sign up or login with your details

Forgot password? Click here to reset