Search Results for author: Ilya Gusev

Found 9 papers, 7 papers with code

Don't lose the message while paraphrasing: A study on content preserving style transfer

1 code implementation17 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.

Style Transfer Text Style Transfer

Russian Texts Detoxification with Levenshtein Editing

1 code implementation28 Apr 2022 Ilya Gusev

Text detoxification is a style transfer task of creating neutral versions of toxic texts.

Style Transfer

HeadlineCause: A Dataset of News Headlines for Detecting Causalities

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.

Commonsense Causal Reasoning Common Sense Reasoning +1

Russian News Clustering and Headline Selection Shared Task

1 code implementation3 May 2021 Ilya Gusev, Ivan Smurov

The presented datasets for event detection and headline selection are the first public Russian datasets for their tasks.

Clustering Event Detection +1

Advances of Transformer-Based Models for News Headline Generation

2 code implementations9 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.

Headline Generation named-entity-recognition +6

Dataset for Automatic Summarization of Russian News

2 code implementations19 Jun 2020 Ilya Gusev

Automatic text summarization has been studied in a variety of domains and languages.

Text Summarization valid

Importance of Copying Mechanism for News Headline Generation

1 code implementation25 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.

Headline Generation Text Summarization

Improving part-of-speech tagging via multi-task learning and character-level word representations

no code implementations2 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.

Multi-Task Learning Part-Of-Speech Tagging +2

Cannot find the paper you are looking for? You can Submit a new open access paper.