lingnguВестник НГУ. Серия: Лингвистика и межкультурная коммуникацияNSU Vestnik. Series: Linguistics and Intercultural Communication1818-7935Новосибирский государственный университет10.25205/1818-7935-2023-21-1-54-66lingngu-519Research ArticleКОМПЬЮТЕРНАЯ И ПРИКЛАДНАЯ ЛИНГВИСТИКАCOMPUTER AND APPLIED LINGUISTICSГенерация ключевых слов для аннотаций русскоязычных научных статейKeyphrase Generation for Abstracts of the Russian-Language Scientific Articleshttps://orcid.org/0000-0003-4464-1355МорозовД. А.MorozovD. A.

Морозов Дмитрий Алексеевич, младший научный сотрудник Лаборатории прикладных цифровых технологий Международного математического центра

Новосибирск

Dmitry A. Morozov, junior researcher, Laboratory of Applied Digital Technologies, Mathematical Center in Akademgorodok

Novosibirsk

morozowdm@gmail.comhttps://orcid.org/0000-0001-8409-6457ГлазковаА. В.GlazkovaA. V.

Глазкова Анна Валерьевна, канд. тех. наук, доцент кафедры программного обеспечения Института математики и компьютерных наук

Тюмень

Anna V. Glazkova, Cand. Sc. (Technology), Associate Professor, Department of Software, Institute of Mathematics and Computer Science 

Tyumen

a.v.glazkova@utmn.ruhttps://orcid.org/0000-0001-5367-3944ТютюльниковМ. А.TyutyulnikovM. A.

Тютюльников Михаил Андреевич, инженер, Лаборатория прикладных цифровых технологий Международного математического центра

Новосибирск

Mikhail A. Tyutyulnikov, engineer, Laboratory of Applied Digital Technologies, Mathematical Center in Akademgorodok

Novosibirsk

mishatyty@gmail.comhttps://orcid.org/0000-0002-1767-5480ИомдинБ. Л.IomdinB. L.

Иомдин Борис Леонидович, канд. филол. наук, ведущий научный сотрудник

Москва

Boris L. Iomdin, Cand. Sc. (Philology), Leading Researcher 

Moscow

iomdin@ruslang.ruНовосибирский государственный университетРоссияNovosibirsk State UniversityRussian FederationТюменский государственный университетРоссияUniversity of TyumenRussian FederationИнститут русского языка им. В. В. Виноградова РАНРоссияVinogradov Russian Language Institute of the Russian Academy of SciencesRussian Federation2023300520232115466Copyright © Морозов Д.А., Глазкова А.В., Тютюльников М.А., Иомдин Б.Л., 20232023Морозов Д.А., Глазкова А.В., Тютюльников М.А., Иомдин Б.Л.Morozov D.A., Glazkova A.V., Tyutyulnikov M.A., Iomdin B.L.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://lingngu.elpub.ru/jour/article/view/519

В этой работе мы попробовали адаптировать различные известные механизмы генерации ключевых слов к весьма специфичному корпусу: аннотациям русскоязычных научных статей из области математики и компьютерных наук. В такой постановке сразу несколько сложностей: отсутствие масштабных исследований механизмов генерации для русского языка, отсутствие крупных корпусов аннотаций и в целом длина аннотаций: если для полного текста ключевые слова обычно встречаются в статье и достаточно лишь выделить их, для аннотаций характерно отсутствие ключевых слов в тексте в явном виде. При этом в открытый доступ попадают обычно именно аннотации, и автоматическая генерация ключевых слов для них позволила бы существенно улучшить возможности поиска по статьям. Причем генерировать слова стоит и для тех статей, в которых авторы сами их указали, так как в ходе исследования мы обнаружили, что используемые ключевые слова нередко уникальны для конкретной статьи, а значит, по таким словам невозможно сформировать подкорпус статей по заданной тематике. Для визуализации результатов работы мы создали ресурс keyphrases.mca.nsu.ru, на котором начинающие исследователи могут сформировать приблизительный список слов для своей первой публикации.

In this paper, we attempted to adapt various well-known algorithms for keyword selection to a very specific text corpus containing abstracts of Russian academic papers from the mathematical and computer science domain. We faced several challenges including the lack of research in the field of keyword extraction for Russian, the absence of large text corpora of academic abstracts, and the insufficient length of the abstracts. Keywords are often found in the full text of the paper and can simply be highlighted, whereas abstracts may not include keywords in an explicit form. At the same time, it is abstracts that are usually in the public domain, so automatic selection of keywords from them would significantly facilitate the process of searching for papers. Moreover, an automatic keyword selection would be useful even for papers for which keywords were already specified by the authors. During the study, we found that authors often use unique keywords for their papers. This complicates their systematization on a given topic. For visualizing the results, we have created a web resource keyphrases.mca.nsu.ru, where young/beginning scholars can form an approximate list of keywords for their first research paper.

статьеотсутствие крупных корпусов аннотацийсловацелом длина аннотацийключевыеarticlelack of large corpora of abstractswordsoverall length of annotationskeyРабота выполнена в рамках проекта № МК-3118.2022, поддержанного грантом Президента Российской Федерации для молодых ученых – кандидатов наук.The work was carried out within the framework of project No. MK-3118.2022, supported by a grant from the President of the Russian Federation for young scientists - candidates of science.ReferencesТихонова Е. В., Косычева М. А. Эффективные ключевые слова: стратегии формулирования // Health, Food & Biotechnology. 2021. № 4 (3). С. 7–15.Boudin, F. PKE: an open source python-based keyphrase extraction toolkit. Proceedings of COLING 2016, the 26th international conference on computational linguistics: system demonstrations. Osaka, Japan, 2016, pp. 69–73.Шереметьева С. О., Осминин П. Г. Методы и модели автоматического извлечения ключевых слов // Вестник Южно-Уральского государственного университета. Серия: Лингвистика. 2015. № 1 (12). С. 76–81.Bougouin, A., Boudin, F., Daille, B. TopicRank: Graph-based topic ranking for keyphrase extraction. Proceedings of the Sixth International Joint Conference on Natural Language Processing. Nagoya, Japan, 2013, pp. 543–551.Boudin F. PKE: an open source python-based keyphrase extraction toolkit // Proceedings of COLING 2016, the 26th international conference on computational linguistics: system demonstrations / ed. by H. Watanabe. The COLING 2016 Organizing Committee. 2016. Pp. 69–73.Campos, R., Mangaravite, V., Pasquali, A., Jorge, A., Nunes, C., Jatowt, A. YAKE! Keyword extraction from single documents using multiple local features. Information Sciences, 2020, 509, pp. 257–289.Bougouin A., Boudin F., Daille B. TopicRank: Graph-based topic ranking for keyphrase extraction // Proceedings of the Sixth International Joint Conference on Natural Language Processing / ed. by R. Mitkov and J. C. Park. Asian Federation of Natural Language Processing. 2013. Pp. 543–551.Chen, W., Chan, H. P., Li, P., King, I. Exclusive Hierarchical Decoding for Deep Keyphrase Generation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online, 2020, pp. 1095–1105.Campos R., Mangaravite V., Pasquali A., Jorge A., Nunes C., Jatowt A. YAKE! Keyword extraction from single documents using multiple local features // Information Sciences. 2020. 509. Pp. 257–289.Devlin, J., Chang, M. W., Lee, K., Toutanova, K. BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT. Minneapolis, USA, 2019, pp. 4171–4186.Chen W., Chan H. P., Li P., King I. Exclusive Hierarchical Decoding for Deep Keyphrase Generation // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics / ed. by D. Jurafsky, J. Chai, N. Schluter and J. Tetreault. Association for Computational Linguistics. 2020. Pp. 1095–1105.El-Beltagy, S. R., Rafea, A. KP-Miner: A keyphrase extraction system for English and Arabic documents. Information Systems, 2009, no. 1 (34), pp. 132–144.Devlin J., Chang M. W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding // Proceedings of NAACL-HLT / ed. by J. Burstein, C. Doran, T. Solorio. Association for Computational Linguistics. 2019. Pp. 4171–4186.Ghanbarpour, A., Naderi, H. A model-based method to improve the quality of ranking in keyword search systems using pseudo-relevance feedback. Journal of Information Science, 2019, no. 4 (45), pp. 473–487.El-Beltagy S. R., Rafea A. KP-Miner: A keyphrase extraction system for English and Arabic documents // Information Systems. 2009. № 1 (34). Pp. 132–144.Grootendorst, M. KeyBERT: Minimal Keyword Extraction with BERT, 2020. Available at: http://doi.org/10.5281/zenodo.4461265 (accessed 29.11.2022).Ghanbarpour A., Naderi H. A model-based method to improve the quality of ranking in keyword search systems using pseudo-relevance feedback // Journal of Information Science. 2019. № 4 (45). Pp. 473–487.Harris, Z. S. Distributional structure. Word, 1954. no. 2-3 (10), pp. 146–162.Grootendorst M. KeyBERT: Minimal Keyword Extraction with BERT. 2020 [Электронный ресурс]. URL: http://doi.org/10.5281/zenodo.4461265 (дата обращения: 29.11.2022).Koloski, B., Pollak, S., Škrlj, B., Martinc, M. Extending Neural Keyword Extraction with TF-IDF tagset matching. Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation. Online, 2021, pp. 22–29.Harris Z. S. Distributional structure // Word. 1954. № 2-3 (10). Pp. 146–162.Korobov, M. Morphological analyzer and generator for Russian and Ukrainian languages. International conference on analysis of images, social networks and texts. Yekaterinburg, 2015, pp. 320–332.Koloski B., Pollak S., Škrlj B., Martinc M. Extending Neural Keyword Extraction with TF-IDF tagset matching // Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation / ed. by H. Toivonen, M. Boggia. Association for Computational Linguistics. 2021. Pp. 22–29.Kuratov, Y., Arkhipov, M. Adaptation of deep bidirectional multilingual transformers for Russian language. Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2019”. Moscow, 2019. Available at: https://www.dialog-21.ru/media/4606/kuratovyplusarkhipovm-025.pdf (accessed 29.11.2022).Korobov M. Morphological analyzer and generator for Russian and Ukrainian languages // International conference on analysis of images, social networks and texts / ed. by M. Yu. Khachay, N. Konstantinova, A. Panchenko, D. Ignatov, V. G. Labunets. Springer, Cham. 2015. Pp. 320–332.Lin C. Y. ROUGE: A package for automatic evaluation of summaries. Text summarization branches out. Osaka, Japan, 2004, pp. 74–81.Kuratov Y., Arkhipov M. Adaptation of deep bidirectional multilingual transformers for Russian language // Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2019”. 2019 [Электронный ресурс]. URL: https://www.dialog-21.ru/media/4606/kuratovyplusarkhipovm-025.pdf (дата обращения: 29.11.2022).Meng, R., Zhao, S., Han, S., He, D., Brusilovsky, P., Chi, Y. Deep Keyphrase Generation. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Vancouver, Canada, 2017, pp. 582–592.Lin C. Y. ROUGE: A package for automatic evaluation of summaries // Text summarization branches out. Association for Computational Linguistics. 2004. Pp. 74–81.Mihalcea, R., Tarau, P. TextRank: Bringing order into text. Proceedings of the 2004 conference on empirical methods in natural language processing. Barcelona, Spain, 2004, pp. 404–411.Meng R., Zhao S., Han S., He D., Brusilovsky P., Chi Y. Deep Keyphrase Generation // Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) / ed. by R. Barzilay, M.-Y. Kan. Association for Computational Linguistics. 2017. Pp. 582–592.Morozov, D., Glazkova, A. Keyphrases CS&Math Russian, Mendeley Data, 2022. Available at: http://doi.org/10.17632/dv3j9wc59v.1 (accessed 29.11.2022).Mihalcea R., Tarau Pp. TextRank: Bringing order into text // Proceedings of the 2004 conference on empirical methods in natural language processing / ed. by D. Lin, D. Wu. Association for Computational Linguistics. 2004. Pp. 404–411.Page L., Brin S., Motwani R., Winograd T. The PageRank citation ranking: Bringing order to the web, Stanford InfoLab, 1998. Available at: http://ilpubs.stanford.edu:8090/422/1/1999-66.pdf (accessed 02.12.2022).Morozov D., Glazkova A. Keyphrases CS&Math Russian, Mendeley Data. 2022 [Электронный ресурс]. URL: http://doi.org/10.17632/dv3j9wc59v.1 (дата обращения: 29.11.2022).Sandul, M., Mikhailova, E. Keyword extraction from single Russian document. Proceedings of the Third Conference on Software Engineering and Information Management (full papers). Saint Petersburg, 2018, pp. 30–36.Page L., Brin S., Motwani R., Winograd T. The PageRank citation ranking: Bringing order to the web. Stanford InfoLab. 1998 [Электронный ресурс]. URL: http://ilpubs.stanford.edu:8090/422/1/1999-66.pdf (дата обращения: 02.12.2022).Sheremetyeva, S. O., Osminin, P. G. [On Methods and Models of Keywords Automatic Extraction]. Vestnik Juzhno-Ural’skogo gosudarstvennogo universiteta. Serija: Lingvistika [Bulletin of South Ural State University, Series «Linguistics»], 2015, no. 1 (12), pp. 76–81. (In Russ.)Sandul M., Mikhailova E. Keyword extraction from single Russian document // Proceedings of the Third Conference on Software Engineering and Information Management (full papers) / ed. by Y. Litvinov, M. Akhin, B. Novikov ,V. Itsykson. CEUR Workshop Proceedings, 2018. Pp. 30–36.Sokolova, E., Moskvina, A., Mitrofanova, O. Keyphrase Extraction from the Russian Corpus on Linguistics by Means of KEA and RAKE Algorithms. Data analytics and management in data intensive domains: Proceedings of the XX International Conference – DAMDID/RCDL’2018. Moscow, 2018, pp. 369–372.Sokolova E., Moskvina A., Mitrofanova O. Keyphrase Extraction from the Russian Corpus on Linguistics by Means of KEA and RAKE Algorithms // Data analytics and management in data intensive domains: Proceedings of the XX International Conference – DAMDID/RCDL’2018 / ed. by L. Kalinichenko, Y. Manolopoulos, S. Stupnikov, N. Skvortsov, V. Sukhomlin. FRC CSC RAS, 2018. Pp. 369–372.Tikhonova, E. V., Kosycheva, M. A. Effective Keywords: Strategies for Their Formulation. Health, Food & Biotechnology, 2021, no. 4 (3), pp. 7–15. (In Russ.)Wienecke Y. Automatic Keyphrase Extraction From Russian-Language Scholarly Papers in Computational Linguistics: University Honors Theses. Portland State University, 2020. 36 p.Wienecke, Y. Automatic Keyphrase Extraction From Russian-Language Scholarly Papers in Computational Linguistics: University Honors Theses. Portland State University, 2020. 36 p.Witten I. H., Paynter G. W., Frank E., Gutwin C., Nevill-Manning C. G. KEA: Practical automatic keyphrase extraction // Proceedings of the fourth ACM conference on Digital libraries / ed. by N. Rowe, E. A. Fox. Association for Computing Machinery, 1999. Pp. 254–255.Witten, I. H., Paynter, G. W., Frank, E., Gutwin, C., Nevill-Manning, C. G. KEA: Practical automatic keyphrase extraction. Proceedings of the fourth ACM conference on Digital libraries. Berkeley, USA, 1999, pp. 254–255.Zhang T., Kishore V., Wu F., Weinberger K. Q., Artzi Y. BERTScore: Evaluating Text Generation with BERT // International Conference on Learning Representations. 2019 [Электронный ресурс]. URL: https://openreview.net/pdf?id=SkeHuCVFDr (дата обращения: 29.11.2022).Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., Artzi, Y. BERTScore: Evaluating Text Generation with BERT. International Conference on Learning Representations. Online, 2019 Available at: https://openreview.net/pdf?id=SkeHuCVFDr (accessed 29.11.2022).

The authors declare that there are no conflicts of interest present.