no code implementations • 23 Sep 2022 • Ekaterina Garmash, Edgar Tanaka, Ann Clifton, Joana Correia, Sharmistha Jat, Winstead Zhu, Rosie Jones, Jussi Karlgren
In this paper we describe the Portuguese-language podcast dataset we have released for academic research purposes.
1 code implementation • 13 Sep 2021 • Lisa Bylinina, Alexey Tikhonov, Ekaterina Garmash
We investigate a new linguistic generalization in pre-trained language models (taking BERT (Devlin et al., 2019) as a case study).
no code implementations • COLING 2016 • Ekaterina Garmash, Christof Monz
We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i. e., multi-source ensembles, a method recently introduced by Firat et al. (2016).