NLP in the age of monolithic large language models is approaching its limits in terms of size and information that can be handled. The trend goes to modularization, a necessary step into the direction of designing smaller sub-networks and components with specialized functionality. In this paper, we present the MAMMOTH toolkit: a framework designed for training massively multilingual modular machine translation systems at scale, initially derived from OpenNMT-py and then adapted to ensure efficient training across computation clusters.We showcase its efficiency across clusters of A100 and V100 NVIDIA GPUs, and discuss our design philosophy and plans for future information.The toolkit is publicly available online at https://github.com/Helsinki-NLP/mammoth.

This paper presents the system description of the NordicsAlps team for the AmericasNLP 2024 Machine Translation Shared Task 1. We investigate the effect of tokenization on translation quality by exploring two different tokenization schemes: byte-level and redundancy-driven tokenization. We submitted three runs per language pair. The redundancy-driven tokenization ranked first among all submissions, scoring the highest average chrF2++, chrF, and BLEU metrics (averaged across all languages). These findings demonstrate the importance of carefully tailoring the tokenization strategies of machine translation systems, particularly in resource-constrained scenarios.

Modularity is a paradigm of machine translation with the potential of bringing forth models that are large at training time and small during inference. Within this field of study, modular approaches, and in particular attention bridges, have been argued to improve the generalization capabilities of models by fostering language-independent representations. In the present paper, we study whether modularity affects translation quality; as well as how well modular architectures generalize across different evaluation scenarios. For a given computational budget, we find non-modular architectures to be always comparable or preferable to all modular designs we study.

In this paper, we present two deep learning approaches that are based on AraBERT, submitted to the Nuanced Arabic Dialect Identification (NADI) shared task of the Seventh Workshop for Arabic Natural Language Processing (WANLP 2022). NADI consists of two main sub-tasks, mainly country-level dialect and sentiment identification for dialectical Arabic. We present one system per sub-task. The first system is a multi-task learning model that consists of a shared AraBERT encoder with three task-specific classification layers. This model is trained to jointly learn the country-level dialect of the tweet as well as the region-level and area-level dialects. The second system is a distilled model of an ensemble of models trained using K-fold cross-validation. Each model in the ensemble consists of an AraBERT model and a classifier, fine-tuned on (K-1) folds of the training set. Our team Pythoneers achieved rank 6 on the first test set of the first sub-task, rank 9 on the second test set of the first sub-task, and rank 4 on the test set of the second sub-task.

In this paper, we present two deep learning approaches that are based on AraBERT, submitted to the Propaganda Detection shared task of the Seventh Workshop for Arabic Natural Language Processing (WANLP 2022). Propaganda detection consists of two main sub-tasks, mainly propaganda identification and span extraction. We present one system per sub-task. The first system is a Multi-Task Learning model that consists of a shared AraBERT encoder with task-specific binary classification layers. This model is trained to jointly learn one binary classification task per propaganda method. The second system is an AraBERT model with a Conditional Random Field (CRF) layer. We achieved rank 3 on the first sub-task and rank 1 on the second sub-task.