Related papers: Leveraging Synthetic Targets for Machine Translation

URL: http://arxiv.org/abs/2305.06155v1
Date: Sun, 7 May 2023 07:42:22 GMT
Title: Leveraging Synthetic Targets for Machine Translation
Authors: Sarthak Mittal, Oleksii Hrinchuk, Oleksii Kuchaiev
Abstract summary: We show that training models on synthetic targets outperforms training on the actual ground-truth data. We provide preliminary analysis into whether this boost in performance is linked to ease of optimization or more deterministic nature of the predictions.
Score: 5.302421715411791
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model. We show that consistently across different benchmarks in bilingual, multilingual, and speech translation setups, training models on synthetic targets outperforms training on the actual ground-truth data. This performance gap grows bigger with increasing limits on the amount of available resources in the form of the size of the dataset and the number of parameters in the model. We also provide preliminary analysis into whether this boost in performance is linked to ease of optimization or more deterministic nature of the predictions, and whether this paradigm leads to better out-of-distribution performance across different testing domains.

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.