Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation
This work addresses the need for more efficient fine-tuning in machine translation by leveraging test set information, though it appears incremental as it builds on existing transductive and data selection methods.
The paper tackles the problem of adapting neural machine translation models to specific test sets by using transductive data selection algorithms to retrieve relevant sentences from a larger parallel dataset, resulting in improved performance over generic or domain-adapted models with a small subset of data.
Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a technique for adapting an NMT model to some domain. In this work, we want to use this technique to adapt the model to a given test set. In particular, we are using transductive data selection algorithms which take advantage the information of the test set to retrieve sentences from a larger parallel set. In cases where the model is available at translation time (when the test set is provided), it can be adapted with a small subset of data, thereby achieving better performance than a generic model or a domain-adapted model.