In plain words: A free, open-source app lets anyone build and run neural translation models without coding, handling data splits, training graphs, tuning, testing, and deployment through simple menus. It also reports the power and carbon used, unlike typical toolkits that require manual setup.
Abstract · adaptNMT: an open-source, language-agnostic development environment for Neural Machine Translation
adaptNMT streamlines all processes involved in the development and deployment of RNN and Transformer neural translation models. As an open-source application, it is designed for both technical and non-technical users who work in the field of machine translation. Built upon the widely-adopted OpenNMT ecosystem, the application is particularly useful for new entrants to the field since the setup of the development environment and creation of train, validation and test splits is greatly simplified. Graphing, embedded within the application, illustrates the progress of model training, and SentencePiece is used for creating subword segmentation models. Hyperparameter customization is facilitated through an intuitive user interface, and a single-click model development approach has been implemented. Models developed by adaptNMT can be evaluated using a range of metrics, and deployed as a translation service within the application. To support eco-friendly research in the NLP space, a green report also flags the power consumption and kgCO$_{2}$ emissions generated during model development. The application is freely available.
Séamus Lankford, Haithem Afli, Andy Way
arXiv:2403.02367 · cs.CL, cs.AI · submitted Mar 4, 2024
abstract · pdf · html