KFU. Card publication. Using Generative Adversarial Networks for Relevance Evaluation of Search Engine Results

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

USING GENERATIVE ADVERSARIAL NETWORKS FOR RELEVANCE EVALUATION OF SEARCH ENGINE RESULTS

Form of presentation

Articles in international journals and collections

Year of publication

2020

��

��

Authors, employees of KFU

Bukharaev Nail Raisovich, author

Bibliographic description in the original language

Dmitry N. Galanin, Nail R. Bukharaev, Alexander M. Gusenkov, Alina R. Sittikova. Using Generative Adversarial Networks for Relevance Evaluation of Search Engine Results / Proceedings of 2020 IEEE East-West Design & Test Symposium (EWDTS) Varna, Bulgaria, September 4 – 7, 2020 pp/ 288-294

Annotation

Proceedings of 2020 IEEE East-West Design & Test Symposium (EWDTS) Varna, Bulgaria, September 4 – 7, 2020

Keywords

Generative adversarial networks, machine learn- ing, information retrieval

The name of the journal

Proceedings of 2020 IEEE East-West Design & Test Symposium (EWDTS) Varna, Bulgaria, September 4 – 7, 2020

URL

https://www.computer.org/csdl/proceedings-article/ewdts/2020/09224840/1nWNUpU1u2Q

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=239748&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Bukharaev Nail Raisovich	ru_RU
dc.date.accessioned	2020-01-01T00:00:00Z	ru_RU
dc.date.available	2020-01-01T00:00:00Z	ru_RU
dc.date.issued	2020	ru_RU
dc.identifier.citation	Dmitry N. Galanin, Nail R. Bukharaev, Alexander M. Gusenkov, Alina R. Sittikova. Using Generative Adversarial Networks for Relevance Evaluation of Search Engine Results / Proceedings of 2020 IEEE East-West Design & Test Symposium (EWDTS) Varna, Bulgaria, September 4 – 7, 2020 pp/ 288-294	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=239748&p_lang=2	ru_RU
dc.description.abstract	Proceedings of 2020 IEEE East-West Design & Test Symposium (EWDTS) Varna, Bulgaria, September 4 – 7, 2020	ru_RU
dc.description.abstract	In the article a new approach to the problem of relevance evaluation of the search engine results, based on generative adversarial networks (GAN), is proposed. To improve the quality of search, the generative adversarial networks are used to distinguish between relevant and irrelevant search results. We used a simplistic model based on fully automated reference results selection and multi-layered generator and discriminator networks with dense layers. The queries needed to generate the reference results were themselves generated by a GPT-2 like network using the same text corpus as a source, to make them potentially relevant to the search space. The results clearly demonstrate the principal possibility and feasibility of using the described approach, despite the fact of used models being simplistic.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	Generative adversarial networks	ru_RU
dc.subject	machine learn- ing	ru_RU
dc.subject	information retrieval	ru_RU
dc.title	Using Generative Adversarial Networks for Relevance Evaluation of Search Engine Results	ru_RU
dc.type	Articles in international journals and collections	ru_RU