Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Gusev Ilya"'
Autor:
Gusev, Ilya
We introduce a novel benchmark for evaluating the role-playing capabilities of language models. Our approach leverages language models themselves to emulate users in dynamic, multi-turn conversations and to assess the resulting dialogues. The framewo
Externí odkaz:
http://arxiv.org/abs/2409.06820
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. Solving the task is not
Externí odkaz:
http://arxiv.org/abs/2308.09055
Autor:
Vlasova Irina, Romanchuk Anna, Gusev Ilya, Volkova Anna, Zakharova Elena, Rzhevskaia Alexandra, Kalmykov Stepan
Publikováno v:
E3S Web of Conferences, Vol 98, p 10008 (2019)
The work is devoted to the study of the behavior of long-lived alpha-emitting radionuclides (Pu, Am, U, Np) under the conditions of injection of acidic liquid radioactive waste into a sandy rock reservoir bed. Different mineral phases of initial rese
Externí odkaz:
https://doaj.org/article/915b1e5d33154cca87d544ea9f705d82
Autor:
Gusev, Ilya
Text detoxification is a style transfer task of creating neutral versions of toxic texts. In this paper, we use the concept of text editing to build a two-step tagging-based detoxification model using a parallel corpus of Russian texts. With this mod
Externí odkaz:
http://arxiv.org/abs/2204.13638
Autor:
Gusev, Ilya, Tikhonov, Alexey
Detecting implicit causal relations in texts is a task that requires both common sense and world knowledge. Existing datasets are focused either on commonsense causal reasoning or explicit causal relations. In this work, we present HeadlineCause, a d
Externí odkaz:
http://arxiv.org/abs/2108.12626
Autor:
Gusev, Ilya, Smurov, Ivan
This paper presents the results of the Russian News Clustering and Headline Selection shared task. As a part of it, we propose the tasks of Russian news event detection, headline selection, and headline generation. These tasks are accompanied by data
Externí odkaz:
http://arxiv.org/abs/2105.00981
Autor:
Bukhtiyarov, Alexey, Gusev, Ilya
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 is a special kind of text summa
Externí odkaz:
http://arxiv.org/abs/2007.05044
Autor:
Gusev, Ilya
Publikováno v:
In: AINL 2020. Communications in Computer and Information Science, vol 1292. Springer, Cham (2020)
Automatic text summarization has been studied in a variety of domains and languages. However, this does not hold for the Russian language. To overcome this issue, we present Gazeta, the first dataset for summarization of Russian news. We describe the
Externí odkaz:
http://arxiv.org/abs/2006.11063
Autor:
Gusev, Ilya
Publikováno v:
Computational Linguistics and Intellectual Technologies, Papers from the Annual International Conference "Dialogue" (2019) Issue 18, 229-236
News headline generation is an essential problem of text summarization because it is constrained, well-defined, and is still hard to solve. Models with a limited vocabulary can not solve it well, as new named entities can appear regularly in the news
Externí odkaz:
http://arxiv.org/abs/1904.11475
Publikováno v:
Computational Linguistics and Intellectual Technologies, Papers from the Annual International Conference "Dialogue" (2018) Issue 17, 14-27
In this paper, we explore the ways to improve POS-tagging using various types of auxiliary losses and different word representations. As a baseline, we utilized a BiLSTM tagger, which is able to achieve state-of-the-art results on the sequence labell
Externí odkaz:
http://arxiv.org/abs/1807.00818