@inproceedings{yang-anderson-2024-evaluating,
title = "Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark",
author = "Yang, Funing and
Anderson, Carolyn Jane",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Miyagawa, So and
Alnajjar, Khalid and
Bizzoni, Yuri},
booktitle = "Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities",
month = nov,
year = "2024",
address = "Miami, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4dh-1.3",
pages = "17--30",
abstract = "Several systems have been developed to extract information about characters to aid computational analysis of English literature. We propose character similarity grouping as a holistic evaluation task for these pipelines. We present AustenAlike, a benchmark suite of character similarities in Jane Austen{'}s novels. Our benchmark draws on three notions of character similarity: a structurally defined notion of similarity; a socially defined notion of similarity; and an expert defined set extracted from literary criticism. We use AustenAlike to evaluate character features extracted using two pipelines, BookNLP and FanfictionNLP. We build character representations from four kinds of features and compare them to the three AustenAlike benchmarks and to GPT-4 similarity rankings. We find that though computational representations capture some broad similarities based on shared social and narrative roles, the expert pairings in our third benchmark are challenging for all systems, highlighting the subtler aspects of similarity noted by human readers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-anderson-2024-evaluating">
<titleInfo>
<title>Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Funing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="given">Jane</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Several systems have been developed to extract information about characters to aid computational analysis of English literature. We propose character similarity grouping as a holistic evaluation task for these pipelines. We present AustenAlike, a benchmark suite of character similarities in Jane Austen’s novels. Our benchmark draws on three notions of character similarity: a structurally defined notion of similarity; a socially defined notion of similarity; and an expert defined set extracted from literary criticism. We use AustenAlike to evaluate character features extracted using two pipelines, BookNLP and FanfictionNLP. We build character representations from four kinds of features and compare them to the three AustenAlike benchmarks and to GPT-4 similarity rankings. We find that though computational representations capture some broad similarities based on shared social and narrative roles, the expert pairings in our third benchmark are challenging for all systems, highlighting the subtler aspects of similarity noted by human readers.</abstract>
<identifier type="citekey">yang-anderson-2024-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4dh-1.3</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>17</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark
%A Yang, Funing
%A Anderson, Carolyn Jane
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Miyagawa, So
%Y Alnajjar, Khalid
%Y Bizzoni, Yuri
%S Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, USA
%F yang-anderson-2024-evaluating
%X Several systems have been developed to extract information about characters to aid computational analysis of English literature. We propose character similarity grouping as a holistic evaluation task for these pipelines. We present AustenAlike, a benchmark suite of character similarities in Jane Austen’s novels. Our benchmark draws on three notions of character similarity: a structurally defined notion of similarity; a socially defined notion of similarity; and an expert defined set extracted from literary criticism. We use AustenAlike to evaluate character features extracted using two pipelines, BookNLP and FanfictionNLP. We build character representations from four kinds of features and compare them to the three AustenAlike benchmarks and to GPT-4 similarity rankings. We find that though computational representations capture some broad similarities based on shared social and narrative roles, the expert pairings in our third benchmark are challenging for all systems, highlighting the subtler aspects of similarity noted by human readers.
%U https://aclanthology.org/2024.nlp4dh-1.3
%P 17-30
Markdown (Informal)
[Evaluating Computational Representations of Character: An Austen Character Similarity Benchmark](https://aclanthology.org/2024.nlp4dh-1.3) (Yang & Anderson, NLP4DH 2024)
ACL