Olesia Koroteeva

Ms. Olesia Koroteeva

ITMO University, St Petersburg, Russia
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 September 2020
Verified
Book Chapter
Closed access
PDF file
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
AMAnton Matveev
Anton Matveev
DBDarya Bogoradnikova
Darya Bogoradnikova
ILInna Lizunova
Inna Lizunova
AMAnna Maltseva
Anna Maltseva
NSNatalia Shilkina
Natalia Shilkina

10 September 2021 in Mathematics
Verified
Journal Article
Open access
PDF file
AMAnton Matveev
Anton Matveev
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
YMYuri N. Matveev
Yuri N. Matveev
ASAleksei Svischev
Aleksei Svischev
PKPolina Korobova
Polina Korobova
AAArtem Akulov
Artem Akulov
A Virtual Dialogue Assistant (VDA) is an automated system intended to provide support for conducting tests and examinations in the context of distant education platforms. Online Distance Learning (ODL) has proven to be a critical part of education systems across the world, particularly during the COVID-19 pandemic. While the core components of ODL are sufficiently researched and developed to become mainstream, there is still a demand for various aspects of traditional classroom learning to be implemented or improved to match the expectations for modern ODL systems. In this work, we take a look at the evaluation of students’ performance. Various forms of testing are often present in ODL systems; however, modern Natural Language Processing (NLP) techniques provide new opportunities to improve this aspect of ODL. In this paper, we present an overview of VDA intended for integration with online education platforms to enhance the process of evaluation of students’ performance. We propose an architecture of such a system, review challenges and solutions for building it, and present examples of solutions for several NLP problems and ways to integrate them into the system. The principal challenge for ODL is accessibility; therefore, proposing an enhancement for ODL systems, we formulate the problem from the point of view of a user interacting with it. In conclusion, we affirm that relying on the advancements in NLP and Machine Learning, the approach we suggest can provide an enhanced experience of evaluation of students’ performance for modern ODL platforms.

10 November 2022
Verified
Book Chapter
Closed access
PDF file
Pavel PosokhovPavel Posokhov
Pavel Posokhov
AMAnastasia Matveeva
Anastasia Matveeva
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
AMAnton Matveev
Anton Matveev
YMYuri N. Matveev
Yuri N. Matveev


8 December 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
YMYuri N. Matveev
Yuri N. Matveev
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
Pavel PosokhovPavel Posokhov
Pavel Posokhov
AMAnton Matveev
Anton Matveev
SSStepan Skrylnikov
Stepan Skrylnikov
In this paper, we present a continuation of our work on the personification of dialogue agents. We expand upon the previously demonstrated models—the ranking and generative models—and propose new hybrid models. Because there is no single definitive way to build a hybrid model, we explore various architectures where the components adopt different roles, sequentially and in parallel. Applying the perplexity and BLEU performance metrics, we discover that the Retrieve and Refine and KG model—a modification of the Retrieve and Refine model where the ranking and generative components work in parallel and compete based on the proximity of the candidate found by the ranking model with a knowledge-grounded generation block—achieves the best performance, with values of 1.64 for perplexity and 0.231 for BLEU scores.

1 April 2024 in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
Verified
Journal Article
Open access
PDF file
KAK.S. Apanasovich
K.S. Apanasovich
Olesia KoroteevaOlesia Koroteeva
Olesia Koroteeva
VKVladimir I. Kabarov
Vladimir I. Kabarov
ODO.P. Dalevskaya
O.P. Dalevskaya
Personalization is one of the keyways to improve the performance of conversational agents. It improves the quality of user interaction with a conversational agent and increases user satisfaction by increasing the consistency and specificity of responses. The dialogue with the agent becomes more consistent, the inconsistency of responses is reduced, and the responses become more specific and interesting. Training and testing personalized conversational agents requires specific datasets containing facts about a persona and texts of persona’s dialogues where replicas use those facts. There are several datasets in English and Chinese containing an average of five facts about a persona where the dialogues are composed by crowdsourcing users who repeatedly imitate different personas. This paper proposes a methodology for collecting an original dataset containing an extended set of facts about a persona and natural dialogues between personas. The new RuPersonaChat dataset is based on three different recording scenarios: an interview, a short conversation, and a long conversation. This is the first dataset for dialogue agent personalization collected which includes both natural dialogues and extended persona’s descriptions. Additionally, in the dataset, the persona’s replicas are annotated with the facts about the persona from which they are generated. The methodology for collecting an original corpus of test data proposed in this paper allows for testing language models for various tasks within the framework of personalized dialogue agent development. The collected dataset includes 139 dialogues and 2608 replicas. This dataset was used to test answer and question generation models and the best results were obtained using the Gpt3-large model (perplexity is equal to 15.7). The dataset can be used to test the personalized dialogue agents’ ability to talk about themselves to the interlocutor, to communicate with the interlocutor utilizing phatic speech and taking into account the extended context when communicating with the user.