@inproceedings{liscio-etal-2022-cross,
title = "Cross-Domain Classification of Moral Values",
author = "Liscio, Enrico and
Dondera, Alin and
Geadau, Andrei and
Jonker, Catholijn and
Murukannaiah, Pradeep",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.209",
doi = "10.18653/v1/2022.findings-naacl.209",
pages = "2727--2745",
abstract = "Moral values influence how we interpret and act upon the information we receive. Identifying human moral values is essential for artificially intelligent agents to co-exist with humans. Recent progress in natural language processing allows the identification of moral values in textual discourse. However, domain-specific moral rhetoric poses challenges for transferring knowledge from one domain to another. We provide the first extensive investigation on the effects of cross-domain classification of moral values from text. We compare a state-of-the-art deep learning model (BERT) in seven domains and four cross-domain settings. We show that a value classifier can generalize and transfer knowledge to novel domains, but it can introduce catastrophic forgetting. We also highlight the typical classification errors in cross-domain value classification and compare the model predictions to the annotators agreement. Our results provide insights to computer and social scientists that seek to identify moral rhetoric specific to a domain of discourse.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liscio-etal-2022-cross">
<titleInfo>
<title>Cross-Domain Classification of Moral Values</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Liscio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alin</namePart>
<namePart type="family">Dondera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrei</namePart>
<namePart type="family">Geadau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catholijn</namePart>
<namePart type="family">Jonker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Murukannaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Moral values influence how we interpret and act upon the information we receive. Identifying human moral values is essential for artificially intelligent agents to co-exist with humans. Recent progress in natural language processing allows the identification of moral values in textual discourse. However, domain-specific moral rhetoric poses challenges for transferring knowledge from one domain to another. We provide the first extensive investigation on the effects of cross-domain classification of moral values from text. We compare a state-of-the-art deep learning model (BERT) in seven domains and four cross-domain settings. We show that a value classifier can generalize and transfer knowledge to novel domains, but it can introduce catastrophic forgetting. We also highlight the typical classification errors in cross-domain value classification and compare the model predictions to the annotators agreement. Our results provide insights to computer and social scientists that seek to identify moral rhetoric specific to a domain of discourse.</abstract>
<identifier type="citekey">liscio-etal-2022-cross</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.209</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.209</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2727</start>
<end>2745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Domain Classification of Moral Values
%A Liscio, Enrico
%A Dondera, Alin
%A Geadau, Andrei
%A Jonker, Catholijn
%A Murukannaiah, Pradeep
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F liscio-etal-2022-cross
%X Moral values influence how we interpret and act upon the information we receive. Identifying human moral values is essential for artificially intelligent agents to co-exist with humans. Recent progress in natural language processing allows the identification of moral values in textual discourse. However, domain-specific moral rhetoric poses challenges for transferring knowledge from one domain to another. We provide the first extensive investigation on the effects of cross-domain classification of moral values from text. We compare a state-of-the-art deep learning model (BERT) in seven domains and four cross-domain settings. We show that a value classifier can generalize and transfer knowledge to novel domains, but it can introduce catastrophic forgetting. We also highlight the typical classification errors in cross-domain value classification and compare the model predictions to the annotators agreement. Our results provide insights to computer and social scientists that seek to identify moral rhetoric specific to a domain of discourse.
%R 10.18653/v1/2022.findings-naacl.209
%U https://aclanthology.org/2022.findings-naacl.209
%U https://doi.org/10.18653/v1/2022.findings-naacl.209
%P 2727-2745
Markdown (Informal)
[Cross-Domain Classification of Moral Values](https://aclanthology.org/2022.findings-naacl.209) (Liscio et al., Findings 2022)
ACL
- Enrico Liscio, Alin Dondera, Andrei Geadau, Catholijn Jonker, and Pradeep Murukannaiah. 2022. Cross-Domain Classification of Moral Values. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2727–2745, Seattle, United States. Association for Computational Linguistics.