SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia

Peerat Limkonchotiwat; Raymond Ng; Sarana Nutanong; Jian Gang Ngui

SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia

Peerat Limkonchotiwat, Raymond Ng, Sarana Nutanong, Jian Gang Ngui

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use ... for bold, ... for italic, ... for underline, <sc>...</sc> for small-caps, <tt>...<tt> for typewriter text, <url>...</url> for URLs, <a href=...> for hyperlinks, and <par/> for paragraph breaks.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-LION-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-LION-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region.

Anthology ID:: 2026.findings-emnlp.1205
Volume:: Findings of the Association for Computational Linguistics: EMNLP 2026
Month:: October
Year:: 2026
Address:: Budapest, Hungary
Editors:: Hung-Yi Lee, Sunipa Dev, Jessy Li, Desmond Elliott
Venue:: Findings
SIG:: SIGDAT
Publisher:: Association for Computational Linguistics
Note:
Pages:: 25455–25463
Language:
URL:: https://aclanthology.org/2026.findings-emnlp.1205/
DOI:
Bibkey:
Cite (ACL):: Peerat Limkonchotiwat, Raymond Ng, Sarana Nutanong, and Jian Gang Ngui. 2026. SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 25455–25463, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):: SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia (Limkonchotiwat et al., Findings 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.findings-emnlp.1205.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{limkonchotiwat-etal-2026-sea,
    title = "{SEA}-{LION}-Embedding: Open and Reproducible Text Embeddings for {S}outheast {A}sia",
    author = "Limkonchotiwat, Peerat  and
      Ng, Raymond  and
      Nutanong, Sarana  and
      Ngui, Jian Gang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1205/",
    pages = "25455--25463",
    ISBN = "979-8-89176-462-0",
    abstract = "Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-LION-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-LION-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="limkonchotiwat-etal-2026-sea">
    <titleInfo>
        <title>SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Peerat</namePart>
        <namePart type="family">Limkonchotiwat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raymond</namePart>
        <namePart type="family">Ng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sarana</namePart>
        <namePart type="family">Nutanong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jian</namePart>
        <namePart type="given">Gang</namePart>
        <namePart type="family">Ngui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-LION-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-LION-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region.</abstract>
    <identifier type="citekey">limkonchotiwat-etal-2026-sea</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1205/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>25455</start>
            <end>25463</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia
%A Limkonchotiwat, Peerat
%A Ng, Raymond
%A Nutanong, Sarana
%A Ngui, Jian Gang
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F limkonchotiwat-etal-2026-sea
%X Text embeddings are fundamental to many downstream applications, making robustness important for real-world NLP. However, most recent state-of-the-art embedding models are not reproducible because they rely on closed or undisclosed training data, and they remain insufficiently robust for Southeast Asian languages. We present SEA-LION-Embedding, a fully open and reproducible text-embedding pipeline for Southeast Asian languages trained only on publicly available data, and use it to study three core factors of robust embedding design: data composition, training objective, and base encoder initialization. SEA-LION-Embedding achieves state-of-the-art results on SEA-BED while enabling systematic and reproducible analysis of robust text embeddings for the region.
%U https://aclanthology.org/2026.findings-emnlp.1205/
%P 25455-25463

Download as File

Markdown (Informal)

[SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia](https://aclanthology.org/2026.findings-emnlp.1205/) (Limkonchotiwat et al., Findings 2026)

SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia (Limkonchotiwat et al., Findings 2026)

ACL

Peerat Limkonchotiwat, Raymond Ng, Sarana Nutanong, and Jian Gang Ngui. 2026. SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 25455–25463, Budapest, Hungary. Association for Computational Linguistics.