no code implementations • LREC (MWE) 2022 • Albina Khusainova, Vitaly Romanov, Adil Khan
Modern encoder-decoder based neural machine translation (NMT) models are normally trained on parallel sentences.
no code implementations • 11 Mar 2021 • Vitaly Romanov, Albina Khusainova
A number of morphology-based word embedding models were introduced in recent years.
no code implementations • WS 2019 • Vitaly Romanov, Albina Khusainova
This paper evaluates morphology-based embeddings for English and Russian languages.
no code implementations • EACL (VarDial) 2021 • Albina Khusainova, Adil Khan, Adín Ramírez Rivera, Vitaly Romanov
The choice of parameter sharing strategy in multilingual machine translation models determines how optimally parameter space is used and hence, directly influences ultimate translation quality.
no code implementations • 1 Oct 2019 • Aidar Valeev, Ilshat Gibadullin, Albina Khusainova, Adil Khan
Neural machine translation is the current state-of-the-art in machine translation.
no code implementations • 1 Oct 2019 • Ilshat Gibadullin, Aidar Valeev, Albina Khusainova, Adil Khan
Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora.
Low-Resource Neural Machine Translation Transfer Learning +1
1 code implementation • 31 Mar 2019 • Albina Khusainova, Adil Khan, Adín Ramírez Rivera
We evaluate state-of-the-art word embedding models for two languages using our proposed datasets for Tatar and the original datasets for English and report our findings on performance comparison.