@inproceedings{schneidermann-etal-2023-probing,
title = "Probing for Hyperbole in Pre-Trained Language Models",
author = "Schneidermann, Nina and
Hershcovich, Daniel and
Pedersen, Bolette",
editor = "Padmakumar, Vishakh and
Vallejo, Gisela and
Fu, Yao",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-srw.30",
doi = "10.18653/v1/2023.acl-srw.30",
pages = "200--211",
abstract = "Hyperbole is a common figure of speech, which is under-explored in NLP research. In this study, we conduct edge and minimal description length (MDL) probing experiments on three pre-trained language models (PLMs) in an attempt to explore the extent to which hyperbolic information is encoded in these models. We use both word-in-context and sentence-level representations as model inputs as a basis for comparison. We also annotate 63 hyperbole sentences from the HYPO dataset according to an operational taxonomy to conduct an error analysis to explore the encoding of different hyperbole categories. Our results show that hyperbole is to a limited extent encoded in PLMs, and mostly in the final layers. They also indicate that hyperbolic information may be better encoded by the sentence-level representations, which, due to the pragmatic nature of hyperbole, may therefore provide a more accurate and informative representation in PLMs. Finally, the inter-annotator agreement for our annotations, a Cohen{'}s Kappa of 0.339, suggest that the taxonomy categories may not be intuitive and need revision or simplification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schneidermann-etal-2023-probing">
<titleInfo>
<title>Probing for Hyperbole in Pre-Trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Schneidermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hershcovich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bolette</namePart>
<namePart type="family">Pedersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishakh</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gisela</namePart>
<namePart type="family">Vallejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hyperbole is a common figure of speech, which is under-explored in NLP research. In this study, we conduct edge and minimal description length (MDL) probing experiments on three pre-trained language models (PLMs) in an attempt to explore the extent to which hyperbolic information is encoded in these models. We use both word-in-context and sentence-level representations as model inputs as a basis for comparison. We also annotate 63 hyperbole sentences from the HYPO dataset according to an operational taxonomy to conduct an error analysis to explore the encoding of different hyperbole categories. Our results show that hyperbole is to a limited extent encoded in PLMs, and mostly in the final layers. They also indicate that hyperbolic information may be better encoded by the sentence-level representations, which, due to the pragmatic nature of hyperbole, may therefore provide a more accurate and informative representation in PLMs. Finally, the inter-annotator agreement for our annotations, a Cohen’s Kappa of 0.339, suggest that the taxonomy categories may not be intuitive and need revision or simplification.</abstract>
<identifier type="citekey">schneidermann-etal-2023-probing</identifier>
<identifier type="doi">10.18653/v1/2023.acl-srw.30</identifier>
<location>
<url>https://aclanthology.org/2023.acl-srw.30</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>200</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing for Hyperbole in Pre-Trained Language Models
%A Schneidermann, Nina
%A Hershcovich, Daniel
%A Pedersen, Bolette
%Y Padmakumar, Vishakh
%Y Vallejo, Gisela
%Y Fu, Yao
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F schneidermann-etal-2023-probing
%X Hyperbole is a common figure of speech, which is under-explored in NLP research. In this study, we conduct edge and minimal description length (MDL) probing experiments on three pre-trained language models (PLMs) in an attempt to explore the extent to which hyperbolic information is encoded in these models. We use both word-in-context and sentence-level representations as model inputs as a basis for comparison. We also annotate 63 hyperbole sentences from the HYPO dataset according to an operational taxonomy to conduct an error analysis to explore the encoding of different hyperbole categories. Our results show that hyperbole is to a limited extent encoded in PLMs, and mostly in the final layers. They also indicate that hyperbolic information may be better encoded by the sentence-level representations, which, due to the pragmatic nature of hyperbole, may therefore provide a more accurate and informative representation in PLMs. Finally, the inter-annotator agreement for our annotations, a Cohen’s Kappa of 0.339, suggest that the taxonomy categories may not be intuitive and need revision or simplification.
%R 10.18653/v1/2023.acl-srw.30
%U https://aclanthology.org/2023.acl-srw.30
%U https://doi.org/10.18653/v1/2023.acl-srw.30
%P 200-211
Markdown (Informal)
[Probing for Hyperbole in Pre-Trained Language Models](https://aclanthology.org/2023.acl-srw.30) (Schneidermann et al., ACL 2023)
ACL
- Nina Schneidermann, Daniel Hershcovich, and Bolette Pedersen. 2023. Probing for Hyperbole in Pre-Trained Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 200–211, Toronto, Canada. Association for Computational Linguistics.