<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-gao-2023-evaluating">
    <titleInfo>
        <title>Evaluating Transformer Models and Human Behaviors on Chinese Character Naming</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaomeng</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lingyu</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Neural network models have been proposed to explain the grapheme-phoneme mapping process in humans for many alphabet languages. These models not only successfully learned the correspondence of the letter strings and their pronunciation, but also captured human behavior in nonce word naming tasks. How would the neural models perform for a non-alphabet language (e.g., Chinese) unknown character task? How well would the model capture human behavior? In this study, we first collect human speakers’ answers on unknown Character naming tasks and then evaluate a set of transformer models by comparing their performance with human behaviors on an unknown Chinese character naming task. We found that the models and humans behaved very similarly, that they had similar accuracy distribution for each character, and had a substantial overlap in answers. In addition, the models’ answers are highly correlated with humans’ answers. These results suggested that the transformer models can capture humans’ character naming behavior well.1</abstract>
    <identifier type="citekey">ma-gao-2023-evaluating</identifier>
    <identifier type="doi">10.1162/tacl_a_00573</identifier>
    <location>
        <url>https://aclanthology.org/2023.tacl-1.44/</url>
    </location>
    <part>
        <date>2023</date>
        <detail type="volume"><number>11</number></detail>
        <extent unit="page">
            <start>755</start>
            <end>770</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Evaluating Transformer Models and Human Behaviors on Chinese Character Naming
%A Ma, Xiaomeng
%A Gao, Lingyu
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F ma-gao-2023-evaluating
%X Neural network models have been proposed to explain the grapheme-phoneme mapping process in humans for many alphabet languages. These models not only successfully learned the correspondence of the letter strings and their pronunciation, but also captured human behavior in nonce word naming tasks. How would the neural models perform for a non-alphabet language (e.g., Chinese) unknown character task? How well would the model capture human behavior? In this study, we first collect human speakers’ answers on unknown Character naming tasks and then evaluate a set of transformer models by comparing their performance with human behaviors on an unknown Chinese character naming task. We found that the models and humans behaved very similarly, that they had similar accuracy distribution for each character, and had a substantial overlap in answers. In addition, the models’ answers are highly correlated with humans’ answers. These results suggested that the transformer models can capture humans’ character naming behavior well.1
%R 10.1162/tacl_a_00573
%U https://aclanthology.org/2023.tacl-1.44/
%U https://doi.org/10.1162/tacl_a_00573
%P 755-770

Markdown (Informal)

[Evaluating Transformer Models and Human Behaviors on Chinese Character Naming](https://aclanthology.org/2023.tacl-1.44/) (Ma & Gao, TACL 2023)

• Evaluating Transformer Models and Human Behaviors on Chinese Character Naming (Ma & Gao, TACL 2023)

ACL

• Xiaomeng Ma and Lingyu Gao. 2023. Evaluating Transformer Models and Human Behaviors on Chinese Character Naming. Transactions of the Association for Computational Linguistics, 11:755–770.