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

TL;DR

This paper introduces MIST, a large annotated dataset of modal verbs in scientific texts, and evaluates neural models for understanding their diverse functions across scientific domains.

Contribution

The paper presents MIST, a new dataset for modal verb functions in scientific texts, and assesses neural models' ability to classify these functions, highlighting domain-specific challenges.

Findings

Neural models achieve moderate accuracy on MIST.

Transfer learning from non-scientific data offers limited benefits.

Scientific communities differ in modal verb usage, but models generalize partially.

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 various NLP tasks such as writing assistance or 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.