MIST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text
This addresses the need for accurate NLP tools in scientific writing and information extraction, but it is incremental as it builds on existing annotation and modeling approaches.
The authors tackled the problem of understanding modal verb functions in scientific text by creating the MIST dataset with 3737 annotated instances and evaluating neural models, finding that transfer from non-scientific data is limited but classifiers generalize across scientific domains.
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.