<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kann-monsalve-mercado-2021-coloring">
    <titleInfo>
        <title>Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Katharina</namePart>
        <namePart type="family">Kann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mauro</namePart>
        <namePart type="given">M</namePart>
        <namePart type="family">Monsalve-Mercado</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Paola</namePart>
            <namePart type="family">Merlo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jorg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Reut</namePart>
            <namePart type="family">Tsarfaty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In contrast to their word- or sentence-level counterparts, character embeddings are still poorly understood. We aim at closing this gap with an in-depth study of English character embeddings. For this, we use resources from research on grapheme–color synesthesia – a neuropsychological phenomenon where letters are associated with colors –, which give us insight into which characters are similar for synesthetes and how characters are organized in color space. Comparing 10 different character embeddings, we ask: How similar are character embeddings to a synesthete’s perception of characters? And how similar are character embeddings extracted from different models? We find that LSTMs agree with humans more than transformers. Comparing across tasks, grapheme-to-phoneme conversion results in the most human-like character embeddings. Finally, ELMo embeddings differ from both humans and other models.</abstract>
    <identifier type="citekey">kann-monsalve-mercado-2021-coloring</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.230</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.230</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>2673</start>
            <end>2685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings
%A Kann, Katharina
%A Monsalve-Mercado, Mauro M.
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F kann-monsalve-mercado-2021-coloring
%X In contrast to their word- or sentence-level counterparts, character embeddings are still poorly understood. We aim at closing this gap with an in-depth study of English character embeddings. For this, we use resources from research on grapheme–color synesthesia – a neuropsychological phenomenon where letters are associated with colors –, which give us insight into which characters are similar for synesthetes and how characters are organized in color space. Comparing 10 different character embeddings, we ask: How similar are character embeddings to a synesthete’s perception of characters? And how similar are character embeddings extracted from different models? We find that LSTMs agree with humans more than transformers. Comparing across tasks, grapheme-to-phoneme conversion results in the most human-like character embeddings. Finally, ELMo embeddings differ from both humans and other models.
%R 10.18653/v1/2021.eacl-main.230
%U https://aclanthology.org/2021.eacl-main.230
%U https://doi.org/10.18653/v1/2021.eacl-main.230
%P 2673-2685

Markdown (Informal)

[Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings](https://aclanthology.org/2021.eacl-main.230) (Kann & Monsalve-Mercado, EACL 2021)

• Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings (Kann & Monsalve-Mercado, EACL 2021)

ACL

• Katharina Kann and Mauro M. Monsalve-Mercado. 2021. Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2673–2685, Online. Association for Computational Linguistics.