no code implementations • 27 Mar 2023 • Elizaveta Korotkova, Isaac Kwan Yin Chung
We demonstrate the need for building brand safety specific datasets via the application of common toxicity detection datasets to a subset of brand safety and empirically analyze the effects of weighted sampling strategies in text classification.
1 code implementation • WMT (EMNLP) 2021 • Maksym Del, Elizaveta Korotkova, Mark Fishel
Here we analyze the sentence representations learned by NMT Transformers and show that these explicitly include the information on text domains, even after only seeing the input sentences without domains labels.
no code implementations • WS 2019 • Andre T{\"a}ttar, Elizaveta Korotkova, Mark Fishel
This paper describes the University of Tartu{'}s submission to the news translation shared task of WMT19, where the core idea was to train a single multilingual system to cover several language pairs of the shared task and submit its results.
no code implementations • 27 Mar 2019 • Elizaveta Korotkova, Agnes Luhtaru, Maksym Del, Krista Liin, Daiga Deksne, Mark Fishel
Both grammatical error correction and text style transfer can be viewed as monolingual sequence-to-sequence transformation tasks, but the scarcity of directly annotated data for either task makes them unfeasible for most languages.
no code implementations • 1 Aug 2018 • Elizaveta Korotkova, Maksym Del, Mark Fishel
We introduce the task of zero-shot style transfer between different languages.