Scientific statement classification over arXiv.org

Ginev D, Miller B (2020)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2020

Publisher: European Language Resources Association (ELRA)

Pages Range: 1219-1226

Conference Proceedings Title: LREC 2020 Conference Proceedings

Event location: Marseille FR

ISBN: 9791095546344

URI: http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.153.pdf

Abstract

We introduce a new classification task for scientific statements and release a large-scale dataset for supervised learning. Our resource is derived from a machine-readable representation of the arXiv.org collection of preprint articles. We explore fifty author-annotated categories and empirically motivate a task design of grouping 10.5 million annotated paragraphs into thirteen classes. We demonstrate that the task setup aligns with known success rates from the state of the art, peaking at a 0.91 F1-score via a BiLSTM encoder-decoder model. Additionally, we introduce a lexeme serialization for mathematical formulas, and observe that context-aware models could improve when also trained on the symbolic modality. Finally, we discuss the limitations of both data and task design, and outline potential directions towards increasingly complex models of scientific discourse, beyond isolated statements.

Authors with CRIS profile

Deyan Ginev Professur für Wissensrepräsentation und -verarbeitung

Involved external institutions

National Institute of Standards and Technology (NIST) US United States (USA) (US)

How to cite

APA:

Ginev, D., & Miller, B. (2020). Scientific statement classification over arXiv.org. In Nicoletta Calzolari, Frederic Bechet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis (Eds.), LREC 2020 Conference Proceedings (pp. 1219-1226). Marseille, FR: European Language Resources Association (ELRA).

MLA:

Ginev, Deyan, and Bruce Miller. "Scientific statement classification over arXiv.org." Proceedings of the 12th International Conference on Language Resources and Evaluation, LREC 2020, Marseille Ed. Nicoletta Calzolari, Frederic Bechet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis, European Language Resources Association (ELRA), 2020. 1219-1226.

BibTeX: Download