Evelina Bakhturina


pdf bib
NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2023
Oleksii Hrinchuk | Vladimir Bataev | Evelina Bakhturina | Boris Ginsburg
Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)

This paper provides an overview of NVIDIA NeMo’s speech translation systems for the IWSLT 2023 Offline Speech Translation Task. This year, we focused on end-to-end system which capitalizes on pre-trained models and synthetic data to mitigate the problem of direct speech translation data scarcity. When trained on IWSLT 2022 constrained data, our best En->De end-to-end model achieves the average score of 31 BLEU on 7 test sets from IWSLT 2010-2020 which improves over our last year cascade (28.4) and end-to-end (25.7) submissions. When trained on IWSLT 2023 constrained data, the average score drops to 29.5 BLEU.


pdf bib
BioMegatron: Larger Biomedical Domain Language Model
Hoo-Chang Shin | Yang Zhang | Evelina Bakhturina | Raul Puri | Mostofa Patwary | Mohammad Shoeybi | Raghav Mani
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

There has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text corpora such as Wikipedia and Books. Yet, most works do not study the factors affecting each domain language application deeply. Additionally, the study of model size on domain-specific models has been mostly missing. We empirically study and evaluate several factors that can affect performance on domain language applications, such as the sub-word vocabulary set, model size, pre-training corpus, and domain transfer. We show consistent improvements on benchmarks with our larger BioMegatron model trained on a larger domain corpus, contributing to our understanding of domain language model applications. We demonstrate noticeable improvements over the previous state-of-the-art (SOTA) on standard biomedical NLP benchmarks of question answering, named entity recognition, and relation extraction. Code and checkpoints to reproduce our experiments are available at [github.com/NVIDIA/NeMo].