Analyzing the prospects for computerized article abstracting as a case study of RNPLS&T’s database “Ecology: Science and technology”
https://doi.org/10.33186/1027-3689-2023-10-99-120
Abstract
The authors examine the possibility of computerized abstracting of publications based on generative abstracting models. They review the approaches toward automatic control including that of neural networks, characterize popular software environments, and discuss their advantages and disadvantages for computerized abstracting. The problems under discussion are relevant as the technology of computerized abstracting increases the accessibility of publications, in particular, those out of the open access while decreases bibliographic processing costs. The authors insist that augmented bibliographic record supplied with annotation or abstract is very important for providing information on new environmental technologies. At the same time, the appropriate abstract consumes intellectual efforts and time of competent professionals. The database “Ecology: Science and Technologies” was chosen as the study object; the database comprises publications on implementation of new environmental-friendly and resource-saving technologies. The authors conclude that computerized abstracting as opposed to similar manual process requires no specialists highly qualified in the discipline of the document being processed while the quality of the abstracts is rather high even when the standard datasets are used.
Keywords
ecology,
abstract,
database,
work standardization,
computerized abstracting,
neural machine translation,
mBARTru generative model,
dataset
Supporting agencies: The article is prepared within the framework of the Government Order to RNPL&T No. 075-01235-23-00 of December 29, 2022 “Developing e-librarianship as a scientific and academic discipline the circumstances of transforming library collections, reference bibliographic and document services in the digital environment” (FNEG-2022-0004), Register No. 720000F.99. 1BN60AV03000 for the years 2022–2024.
About the Authors
E. F. Bychkova
Russian National Public Library for Science and Technology
Russian Federation
Russian Federation
Elena F. Bychkova – Cand. Sc. (Pedagogy), Leading Researcher, Head, Ecology and Sustainable Development Group of Academic Secretary Department
, Moscow
K. A. Kolosov
Russian National Public Library for Science and Technology
Russian Federation
Russian Federation
Kirill A. Kolosov – Cand. Sc. (Engineering), Leading Researcher, Russian National Public Library for Science and Technology; Associate Professor, Moscow State Linguistic University
Moscow
References
1. Salomatova O. I., Zelenina G. N. Vozmozhnosti proekta MARS (Mezhregional`naia analiticheskaia rospis` statei`) v informatcionno-bibliograficheskoi` rabote biblioteki // Biblioteki vuzov Urala: problemy` i opy`t raboty`. 2003. Vy`p. 4. 2003.
2. Leepnitckii` S. F., Mamchich A. A., Sorudei`kina S. A. Veb-poisk i annotirovanie nauchnotekhnicheskoi` informatcii na osnove tematicheskikh korpusov tekstov // Informatika. 2018. T. 1. № 2 (22). S. 114–125.
3. Mukambetova G. I. Annotirovanie i referirovanie dokumentov: problemy` izucheniia pri podgotovke spetcialistov dlia bibliotek // Vestneyk Bishkekskogo gumanitarnogo universiteta. 2009. № 2. S. 242–244.
4. Shrai`berg Ia. L. Bibliotechno-informatcionnaia sfera v sovremenny`kh usloviiakh narastaiushchei` tcifrovizatcii, postpandemii`noi` obstanovki i novy`kh sotcial`nopoliticheskikh realii`: glavny`e rezul`taty` : plenarny`i` doclad Predsedatelia Orgkomiteta Dvadtcat` shestoi` Mezhdunarodnoi` konferentcii i vy`stavki «LIBCOM–2022». Moskva : GPNTB Rossii, 2022. 27 s. : il. Bibliogr.: s. 26–27 (17 nazv.). 350 e`kz. ISBN 978-5-85638253-1. doi: 10.33186/978-5-85638-253-1-2022
5. Solov`yova L. S. Baza danny`kh «E`KO»: osobennosti formirovaniia i obsluzhivaniia pol`zovatelei` // Nauchny`e i tekhnicheskie biblioteki. 2003. № 4. S. 51–53. URL: http://ellib.gpntb.ru/subscribe/index.php?journal=ntb&year=2003&num=4&art=8 (data obrashcheniia: 11.11.2019).
6. By`chkova E. F. Referativnaia BD «E`kologiia: nauka i tekhnologii» – vazhnaia chast` E`lektronnoi` biblioteki GPNTB Rossii po e`kologii // Nauchny`e i tekhnicheskie biblioteki. 2008. № 2. S. 77–84. URL: http://ellib.gpntb.ru/subscribe/index.php?journal=ntb&year=2008& num=2&art=13 (data obrashcheniia: 27.01.2020).
7. Borgoiakova K. S. Bibliometricheskii` analiz nauchny`kh publikatcii` po e`kologii na osnove referativnoi` bazy` danny`kh «E`kologiia: nauka i tekhnologii» GPNTB Rossii // Nauchny`e i tekhnicheskie biblioteki. 2017. № 10. S. 54–68. URL: https://www.gpntb.ru/ntb/ntb/2017/10/NTB10_2017_А5_6.pdf (data obrashcheniia: 20.12.2019).
8. By`chkova E. F. Otrazhenie publikatcii` po teme avarii na Chernoby`l`skoi` AE`S i smezhny`m s nei` voprosam v BD GPNTB Rossii «E`kologiia: nauka i tekhnologii» // Chernoby`l` 35 let spustia : materialy` Mezhgosudarstvennoi` nauchno-prakticheskoi` konferentcii (22 aprelia 2021 g.). Briansk, 2021. S. 30–37.
9. Kratkii` otchyot o deiatel`nosti GPNTB Rossii za 2021 god. URL: https://www.gpntb.ru/ofitsialnye-dokumenty/84--12/ofitsialnye-dokumenty/9672-kratkij-otchet-o-deyatelnosti-gpntb-rossii-za-2022-god.html (data obrashcheniia: 07.09.2023). URL: свободный.
10. Das D., Martins A. A. Survey on Automatic Text Summarization : Technical report // Literature Survey for the Language and Statistics II course at Carnegie Mellon University. Pittsburgh, US, 2007. P. 192–195.
11. Batura T. V., Bakieva A. M. Metody` i sistemy` avtomaticheskogo referirovaniia tekstov. Novosibirsk : IPTC NGU, 2019.
12. Sekrety` generiruiushchego referirovaniia tekstov. URL: https://habr.com/ru/articles/596481 (data obrashcheniia: 12.05.2023).
13. ChatGPT. URL: https://ru.wikipedia.org/wiki/ChatGPT (data obrashcheniia: 12.05.2023).
14. Liu Y., Lapata M. Text summarization with pretrained encoders // arXiv preprint arXiv:1908.08345. 2019. URL: https://arxiv.org/pdf/1908.08345v2.pdf (data obrashcheniia: 12.05.2023).
15. GPT-3. URL: https://ru.wikipedia.org/wiki/GPT-3 (data obrashcheniia: 12.05.2023).
16. RED-T5. Новая SOTA модель для русского языка от SberDevices. URL: https://habr.com/ru/companies/sberdevices/articles/730088 (data obrashcheniia: 12.05.2023).
17. Lewis M. et al. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension // arXiv preprint arXiv:1910.13461. 2019.
18. Luchshee mesto dlia nachala raboty` s iskusstvenny`m intellektom: rukovodstvo po Google Colab dlia nachinaiushchikh. URL: https://digitrain.ru/articles/156113 (data obrashcheniia: 12.05.2023).
19. Kirpichnikova I. M. Utilizatciia vy`brosov CO₂ na e`lektrostantciiakh s ispol`zovaniem bioreaktorov // E`nergosberezhenie i vodopodgotovka. 2022. № 5. S. 15–18.
20. Prikaz Ministerstva kul`tury` RF ot 30 dekabria 2014 g. № 2477 «Ob utverzhdenii tipovy`kh otraslevy`kh norm truda na raboty`, vy`polniaemy`e v bibliotekakh». URL: https://www.garant.ru/products/ipo/prime/doc/70921222 (data obrashcheniia: 12.05.2023).
21. Tikunova I. P. Organizatciia normirovaniia truda v biblioteke : sbornik normativny`kh, metodicheskikh i informatcionny`kh materialov; Rossii`skaia gosudarstvennaia biblioteka [i dr.]. Moskva : Pashkov dom, 2017. 454 s.
22. Normy` truda na raboty`, vy`polniaemy`e v bibliotekakh Korporativnoi` seti obshchedostupny`kh bibliotek Sankt-Peterburga (KSOB SPb) / Central`naia gorodskaia publichnaia biblioteka im. V. V. Maiakovskogo; sostaviteli: Marina Nicolaevna Suhareva [i dr.]. 2-e izd., ispr. i dop. Sankt-Peterburg : TCGPB, 2021. 80 s. : il. (Obshchedostupny`e biblioteki Sankt-Peterburga). Bibliogr.: 77–80 (57 nazv.).
Review
For citations:
Bychkova E.F., Kolosov K.A. Analyzing the prospects for computerized article abstracting as a case study of RNPLS&T’s database “Ecology: Science and technology”. Scientific and Technical Libraries. 2023;1(10):99-120. (In Russ.) https://doi.org/10.33186/1027-3689-2023-10-99-120
Views:
456
Email this article 