Standard

Explicit semantic analysis as a means for topic labelling. / Kriukova, Anna; Erofeeva, Aliia; Mitrofanova, Olga; Sukharev, Kirill.

Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings. ed. / Lidia Pivovarova; Andrey Filchenkov; Jan Zizka; Dmitry Ustalov. Springer Nature, 2018. p. 110-116 (Communications in Computer and Information Science; Vol. 930).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Harvard

Kriukova, A, Erofeeva, A, Mitrofanova, O & Sukharev, K 2018, Explicit semantic analysis as a means for topic labelling. in L Pivovarova, A Filchenkov, J Zizka & D Ustalov (eds), Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings. Communications in Computer and Information Science, vol. 930, Springer Nature, pp. 110-116, 7th International Conference Artificial Intelligence and Natural Language, AINL 2018, St. Petersburg, Russian Federation, 17/10/18. https://doi.org/10.1007/978-3-030-01204-5_11

APA

Kriukova, A., Erofeeva, A., Mitrofanova, O., & Sukharev, K. (2018). Explicit semantic analysis as a means for topic labelling. In L. Pivovarova, A. Filchenkov, J. Zizka, & D. Ustalov (Eds.), Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings (pp. 110-116). (Communications in Computer and Information Science; Vol. 930). Springer Nature. https://doi.org/10.1007/978-3-030-01204-5_11

Vancouver

Kriukova A, Erofeeva A, Mitrofanova O, Sukharev K. Explicit semantic analysis as a means for topic labelling. In Pivovarova L, Filchenkov A, Zizka J, Ustalov D, editors, Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings. Springer Nature. 2018. p. 110-116. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-030-01204-5_11

Author

Kriukova, Anna ; Erofeeva, Aliia ; Mitrofanova, Olga ; Sukharev, Kirill. / Explicit semantic analysis as a means for topic labelling. Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings. editor / Lidia Pivovarova ; Andrey Filchenkov ; Jan Zizka ; Dmitry Ustalov. Springer Nature, 2018. pp. 110-116 (Communications in Computer and Information Science).

BibTeX

@inproceedings{3d3797f9ccf24addb4a1f65a2708439e,
title = "Explicit semantic analysis as a means for topic labelling",
abstract = "This paper deals with a method for topic labelling that makes use of Explicit Semantic Analysis (ESA). Top words of a topic are given to ESA as an input, and the algorithm yields titles of Wikipedia articles that are considered most relevant to the input. An alternative approach that serves as a strong baseline employs titles of first outputs in a search engine, given topic words as a query. In both methods, obtained titles are then automatically analysed and phrases characterizing the topic are constructed from them with the use of a graph algorithm and are assigned with weights. Within the proposed method based on ESA, post-processing is then performed to sort candidate labels according to empirically formulated rules. Experiments were conducted on a corpus of Russian encyclopaedic texts on linguistics. The results justify applying ESA for this task, and we state that though it works a little inferior to the method based on a search engine in terms of labels{\textquoteright} quality, it can be used as a reasonable alternative because it exhibits two advantages that the baseline method lacks.",
keywords = "Explicit Semantic Analysis, Russian, Topic labels, Topic modelling",
author = "Anna Kriukova and Aliia Erofeeva and Olga Mitrofanova and Kirill Sukharev",
note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2018. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; 7th International Conference Artificial Intelligence and Natural Language, AINL 2018 ; Conference date: 17-10-2018 Through 19-10-2018",
year = "2018",
doi = "10.1007/978-3-030-01204-5_11",
language = "English",
isbn = "9783030012038",
series = "Communications in Computer and Information Science",
publisher = "Springer Nature",
pages = "110--116",
editor = "Lidia Pivovarova and Andrey Filchenkov and Jan Zizka and Dmitry Ustalov",
booktitle = "Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings",
address = "Germany",

}

RIS

TY - GEN

T1 - Explicit semantic analysis as a means for topic labelling

AU - Kriukova, Anna

AU - Erofeeva, Aliia

AU - Mitrofanova, Olga

AU - Sukharev, Kirill

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2018. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2018

Y1 - 2018

N2 - This paper deals with a method for topic labelling that makes use of Explicit Semantic Analysis (ESA). Top words of a topic are given to ESA as an input, and the algorithm yields titles of Wikipedia articles that are considered most relevant to the input. An alternative approach that serves as a strong baseline employs titles of first outputs in a search engine, given topic words as a query. In both methods, obtained titles are then automatically analysed and phrases characterizing the topic are constructed from them with the use of a graph algorithm and are assigned with weights. Within the proposed method based on ESA, post-processing is then performed to sort candidate labels according to empirically formulated rules. Experiments were conducted on a corpus of Russian encyclopaedic texts on linguistics. The results justify applying ESA for this task, and we state that though it works a little inferior to the method based on a search engine in terms of labels’ quality, it can be used as a reasonable alternative because it exhibits two advantages that the baseline method lacks.

AB - This paper deals with a method for topic labelling that makes use of Explicit Semantic Analysis (ESA). Top words of a topic are given to ESA as an input, and the algorithm yields titles of Wikipedia articles that are considered most relevant to the input. An alternative approach that serves as a strong baseline employs titles of first outputs in a search engine, given topic words as a query. In both methods, obtained titles are then automatically analysed and phrases characterizing the topic are constructed from them with the use of a graph algorithm and are assigned with weights. Within the proposed method based on ESA, post-processing is then performed to sort candidate labels according to empirically formulated rules. Experiments were conducted on a corpus of Russian encyclopaedic texts on linguistics. The results justify applying ESA for this task, and we state that though it works a little inferior to the method based on a search engine in terms of labels’ quality, it can be used as a reasonable alternative because it exhibits two advantages that the baseline method lacks.

KW - Explicit Semantic Analysis

KW - Russian

KW - Topic labels

KW - Topic modelling

UR - http://www.scopus.com/inward/record.url?scp=85054881717&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01204-5_11

DO - 10.1007/978-3-030-01204-5_11

M3 - Conference contribution

AN - SCOPUS:85054881717

SN - 9783030012038

T3 - Communications in Computer and Information Science

SP - 110

EP - 116

BT - Artificial Intelligence and Natural Language - 7th International Conference, AINL 2018, Proceedings

A2 - Pivovarova, Lidia

A2 - Filchenkov, Andrey

A2 - Zizka, Jan

A2 - Ustalov, Dmitry

PB - Springer Nature

T2 - 7th International Conference Artificial Intelligence and Natural Language, AINL 2018

Y2 - 17 October 2018 through 19 October 2018

ER -

ID: 37684204