Standard

Multi-task fine-tuning for generating keyphrases in a scientific domain. / Glazkova, Anna; Morozov, Dmitry.

Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Glazkova, A & Morozov, D 2023, Multi-task fine-tuning for generating keyphrases in a scientific domain. in Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023. Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ITNT57377.2023.10139061

APA

Glazkova, A., & Morozov, D. (2023). Multi-task fine-tuning for generating keyphrases in a scientific domain. In Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023 (Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITNT57377.2023.10139061

Vancouver

Glazkova A, Morozov D. Multi-task fine-tuning for generating keyphrases in a scientific domain. In Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023). doi: 10.1109/ITNT57377.2023.10139061

Author

Glazkova, Anna ; Morozov, Dmitry. / Multi-task fine-tuning for generating keyphrases in a scientific domain. Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023).

BibTeX

@inproceedings{daf9996fbe0240feae26ca5bd8a8af68,
title = "Multi-task fine-tuning for generating keyphrases in a scientific domain",
abstract = "Automatic selection of keyphrases (keywords) is a major challenge to finding and systematizing scholarly documents. This paper investigates the efficiency of using titles of scientific papers as additional information for keyphrase generation. We propose an approach to multi-task fine-tuning the BART model using control codes1. It is shown that the suggested approach can improve the performance of BART for the task of keyphrase generation. In some cases, the presented model outperforms state-of-the-art models for keyphrase extraction. Moreover, the results have demonstrated that multitask fine-tuning also increases the performance of title generation.",
keywords = "BART, automatic summarization, keyphrase generation, keyword extraction, multi-task learning, natural language processing, scientific text, text generation",
author = "Anna Glazkova and Dmitry Morozov",
note = "This work was supported by the grant of the President of the Russian Federation no. MK-3118.2022.4. Публикация для корректировки.",
year = "2023",
doi = "10.1109/ITNT57377.2023.10139061",
language = "English",
isbn = "9798350397338",
series = "Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023",
address = "United States",

}

RIS

TY - GEN

T1 - Multi-task fine-tuning for generating keyphrases in a scientific domain

AU - Glazkova, Anna

AU - Morozov, Dmitry

N1 - This work was supported by the grant of the President of the Russian Federation no. MK-3118.2022.4. Публикация для корректировки.

PY - 2023

Y1 - 2023

N2 - Automatic selection of keyphrases (keywords) is a major challenge to finding and systematizing scholarly documents. This paper investigates the efficiency of using titles of scientific papers as additional information for keyphrase generation. We propose an approach to multi-task fine-tuning the BART model using control codes1. It is shown that the suggested approach can improve the performance of BART for the task of keyphrase generation. In some cases, the presented model outperforms state-of-the-art models for keyphrase extraction. Moreover, the results have demonstrated that multitask fine-tuning also increases the performance of title generation.

AB - Automatic selection of keyphrases (keywords) is a major challenge to finding and systematizing scholarly documents. This paper investigates the efficiency of using titles of scientific papers as additional information for keyphrase generation. We propose an approach to multi-task fine-tuning the BART model using control codes1. It is shown that the suggested approach can improve the performance of BART for the task of keyphrase generation. In some cases, the presented model outperforms state-of-the-art models for keyphrase extraction. Moreover, the results have demonstrated that multitask fine-tuning also increases the performance of title generation.

KW - BART

KW - automatic summarization

KW - keyphrase generation

KW - keyword extraction

KW - multi-task learning

KW - natural language processing

KW - scientific text

KW - text generation

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85163414123&origin=inward&txGid=2bb414d77865dfe2c854f4a3e11743ae

UR - https://www.mendeley.com/catalogue/6033603b-5b39-3ca4-9928-bc7f25a5bec5/

U2 - 10.1109/ITNT57377.2023.10139061

DO - 10.1109/ITNT57377.2023.10139061

M3 - Conference contribution

SN - 9798350397338

T3 - Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023

BT - Proceedings - 9th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2023

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

ID: 58623887