@inproceedings{wachowiak-gromann-2022-systematic,
title = "Systematic Analysis of Image Schemas in Natural Language through Explainable Multilingual Neural Language Processing",
author = "Wachowiak, Lennart and
Gromann, Dagmar",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.493",
pages = "5571--5581",
abstract = "In embodied cognition, physical experiences are believed to shape abstract cognition, such as natural language and reasoning. Image schemas were introduced as spatio-temporal cognitive building blocks that capture these recurring sensorimotor experiences. The few existing approaches for automatic detection of image schemas in natural language rely on specific assumptions about word classes as indicators of spatio-temporal events. Furthermore, the lack of sufficiently large, annotated datasets makes evaluation and supervised learning difficult. We propose to build on the recent success of large multilingual pretrained language models and a small dataset of examples from image schema literature to train a supervised classifier that classifies natural language expressions of varying lengths into image schemas. Despite most of the training data being in English with few examples for German, the model performs best in German. Additionally, we analyse the model{'}s zero-shot performance in Russian, French, and Mandarin. To further investigate the model{'}s behaviour, we utilize local linear approximations for prediction probabilities that indicate which words in a sentence the model relies on for its final classification decision. Code and dataset are publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wachowiak-gromann-2022-systematic">
<titleInfo>
<title>Systematic Analysis of Image Schemas in Natural Language through Explainable Multilingual Neural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lennart</namePart>
<namePart type="family">Wachowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In embodied cognition, physical experiences are believed to shape abstract cognition, such as natural language and reasoning. Image schemas were introduced as spatio-temporal cognitive building blocks that capture these recurring sensorimotor experiences. The few existing approaches for automatic detection of image schemas in natural language rely on specific assumptions about word classes as indicators of spatio-temporal events. Furthermore, the lack of sufficiently large, annotated datasets makes evaluation and supervised learning difficult. We propose to build on the recent success of large multilingual pretrained language models and a small dataset of examples from image schema literature to train a supervised classifier that classifies natural language expressions of varying lengths into image schemas. Despite most of the training data being in English with few examples for German, the model performs best in German. Additionally, we analyse the model’s zero-shot performance in Russian, French, and Mandarin. To further investigate the model’s behaviour, we utilize local linear approximations for prediction probabilities that indicate which words in a sentence the model relies on for its final classification decision. Code and dataset are publicly available.</abstract>
<identifier type="citekey">wachowiak-gromann-2022-systematic</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.493</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5571</start>
<end>5581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Systematic Analysis of Image Schemas in Natural Language through Explainable Multilingual Neural Language Processing
%A Wachowiak, Lennart
%A Gromann, Dagmar
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F wachowiak-gromann-2022-systematic
%X In embodied cognition, physical experiences are believed to shape abstract cognition, such as natural language and reasoning. Image schemas were introduced as spatio-temporal cognitive building blocks that capture these recurring sensorimotor experiences. The few existing approaches for automatic detection of image schemas in natural language rely on specific assumptions about word classes as indicators of spatio-temporal events. Furthermore, the lack of sufficiently large, annotated datasets makes evaluation and supervised learning difficult. We propose to build on the recent success of large multilingual pretrained language models and a small dataset of examples from image schema literature to train a supervised classifier that classifies natural language expressions of varying lengths into image schemas. Despite most of the training data being in English with few examples for German, the model performs best in German. Additionally, we analyse the model’s zero-shot performance in Russian, French, and Mandarin. To further investigate the model’s behaviour, we utilize local linear approximations for prediction probabilities that indicate which words in a sentence the model relies on for its final classification decision. Code and dataset are publicly available.
%U https://aclanthology.org/2022.coling-1.493
%P 5571-5581
Markdown (Informal)
[Systematic Analysis of Image Schemas in Natural Language through Explainable Multilingual Neural Language Processing](https://aclanthology.org/2022.coling-1.493) (Wachowiak & Gromann, COLING 2022)
ACL