In scientific papers, it is common practice to cite other articles to substantiate claims, provide evidence for factual assertions, reference limitations, and research gaps, and fulfill various other purposes. When authors include a citation in a given sentence, there are two considerations they need to take into account: (i) where in the sentence to place the citation and (ii) which citation to choose to support the underlying claim. In this paper, we focus on the first task as it allows multiple potential approaches that rely on the researcher's individual style and the specific norms and conventions of the relevant scientific community. We propose two automatic methodologies that leverage transformers architecture for either solving a Mask-Filling problem or a Named Entity Recognition problem. On top of the results of the proposed methodologies, we apply ad-hoc Natural Language Processing heuristics to further improve their outcome. We also introduce s2orc-9K, an open dataset for fine-tuning models on this task. A formal evaluation demonstrates that the generative approach significantly outperforms five alternative methods when fine-tuned on the novel dataset. Furthermore, this model's results show no statistically significant deviation from the outputs of three senior researchers.

Buscaldi, D., Dessi, D., Motta, E., Murgia, M., Osborne, F., Reforgiato Recupero, D. (2024). Citation prediction by leveraging transformers and natural language processing heuristics. INFORMATION PROCESSING & MANAGEMENT, 61(1 (January 2024)) [10.1016/j.ipm.2023.103583].

Citation prediction by leveraging transformers and natural language processing heuristics

Osborne, F;
2024

Abstract

In scientific papers, it is common practice to cite other articles to substantiate claims, provide evidence for factual assertions, reference limitations, and research gaps, and fulfill various other purposes. When authors include a citation in a given sentence, there are two considerations they need to take into account: (i) where in the sentence to place the citation and (ii) which citation to choose to support the underlying claim. In this paper, we focus on the first task as it allows multiple potential approaches that rely on the researcher's individual style and the specific norms and conventions of the relevant scientific community. We propose two automatic methodologies that leverage transformers architecture for either solving a Mask-Filling problem or a Named Entity Recognition problem. On top of the results of the proposed methodologies, we apply ad-hoc Natural Language Processing heuristics to further improve their outcome. We also introduce s2orc-9K, an open dataset for fine-tuning models on this task. A formal evaluation demonstrates that the generative approach significantly outperforms five alternative methods when fine-tuned on the novel dataset. Furthermore, this model's results show no statistically significant deviation from the outputs of three senior researchers.
Articolo in rivista - Articolo scientifico
BERT; Citation prediction; Mask-filling; Named entity recognition; Transformers architecture;
English
16-nov-2023
2024
61
1 (January 2024)
103583
open
Buscaldi, D., Dessi, D., Motta, E., Murgia, M., Osborne, F., Reforgiato Recupero, D. (2024). Citation prediction by leveraging transformers and natural language processing heuristics. INFORMATION PROCESSING & MANAGEMENT, 61(1 (January 2024)) [10.1016/j.ipm.2023.103583].
File in questo prodotto:
File Dimensione Formato  
Buscaldi-2024-Inform Process Manag-VoR.pdf

accesso aperto

Descrizione: Research Article
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 1.12 MB
Formato Adobe PDF
1.12 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/453079
Citazioni
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
Social impact