1 code implementation • 17 Aug 2023 • Nikolay Babakov, David Dale, Ilya Gusev, Irina Krotova, Alexander Panchenko
Text style transfer techniques are gaining popularity in natural language processing allowing paraphrasing text in the required form: from toxic to neural, from formal to informal, from old to the modern English language, etc.
1 code implementation • 28 Apr 2022 • Ilya Gusev
Text detoxification is a style transfer task of creating neutral versions of toxic texts.
1 code implementation • LREC 2022 • Ilya Gusev, Alexey Tikhonov
In this work, we present HeadlineCause, a dataset for detecting implicit causal relations between pairs of news headlines.
1 code implementation • 3 May 2021 • Ilya Gusev, Ivan Smurov
The presented datasets for event detection and headline selection are the first public Russian datasets for their tasks.
2 code implementations • 9 Jul 2020 • Alexey Bukhtiyarov, Ilya Gusev
Pretrained language models based on Transformer architecture are the reason for recent breakthroughs in many areas of NLP, including sentiment analysis, question answering, named entity recognition.
2 code implementations • 19 Jun 2020 • Ilya Gusev
Automatic text summarization has been studied in a variety of domains and languages.
Ranked #1 on Text Summarization on Gazeta
1 code implementation • 25 Apr 2019 • Ilya Gusev
News headline generation is an essential problem of text summarization because it is constrained, well-defined, and is still hard to solve.
no code implementations • 2 Jul 2018 • Daniil Anastasyev, Ilya Gusev, Eugene Indenbom
Finally, we designed a new variant of auxiliary loss for sequence labelling tasks: an additional prediction of the neighbour labels.