Nothing Special   »   [go: up one dir, main page]

MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text

Sophie Henning, Nicole Macher, Stefan Grünewald, Annemarie Friedrich


Abstract
Modal verbs (e.g., can, should or must) occur highly frequently in scientific articles. Decoding their function is not straightforward: they are often used for hedging, but they may also denote abilities and restrictions. Understanding their meaning is important for accurate information extraction from scientific text.To foster research on the usage of modals in this genre, we introduce the MIST (Modals In Scientific Text) dataset, which contains 3737 modal instances in five scientific domains annotated for their semantic, pragmatic, or rhetorical function. We systematically evaluate a set of competitive neural architectures on MIST. Transfer experiments reveal that leveraging non-scientific data is of limited benefit for modeling the distinctions in MIST. Our corpus analysis provides evidence that scientific communities differ in their usage of modal verbs, yet, classifiers trained on scientific data generalize to some extent to unseen scientific domains.
Anthology ID:
2022.findings-emnlp.94
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1305–1324
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.94
DOI:
10.18653/v1/2022.findings-emnlp.94
Bibkey:
Cite (ACL):
Sophie Henning, Nicole Macher, Stefan Grünewald, and Annemarie Friedrich. 2022. MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1305–1324, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text (Henning et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.94.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.94.mp4