@inproceedings{henning-etal-2022-mist,
title = "{M}i{ST}: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in {E}nglish Scientific Text",
author = {Henning, Sophie and
Macher, Nicole and
Gr{\"u}newald, Stefan and
Friedrich, Annemarie},
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.94",
doi = "10.18653/v1/2022.findings-emnlp.94",
pages = "1305--1324",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="henning-etal-2022-mist">
<titleInfo>
<title>MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Henning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicole</namePart>
<namePart type="family">Macher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Grünewald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">henning-etal-2022-mist</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.94</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.94</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1305</start>
<end>1324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text
%A Henning, Sophie
%A Macher, Nicole
%A Grünewald, Stefan
%A Friedrich, Annemarie
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F henning-etal-2022-mist
%X 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.
%R 10.18653/v1/2022.findings-emnlp.94
%U https://aclanthology.org/2022.findings-emnlp.94
%U https://doi.org/10.18653/v1/2022.findings-emnlp.94
%P 1305-1324
Markdown (Informal)
[MiST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text](https://aclanthology.org/2022.findings-emnlp.94) (Henning et al., Findings 2022)
ACL