<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="setiawan-etal-2026-mudidi">
    <titleInfo>
        <title>MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="given">Samuel</namePart>
        <namePart type="family">Setiawan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Temuulen</namePart>
        <namePart type="family">Khishigsuren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Milind</namePart>
        <namePart type="family">Agarwal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pagnarith</namePart>
        <namePart type="family">Pit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aso</namePart>
        <namePart type="family">Mahmudi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ekaterina</namePart>
        <namePart type="family">Vylomova</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Multilingual dictionaries are among the most valuable documentary resources for low-resource and endangered languages, yet many remain available only as scans. For many decades their digitization and conversion into a machine-readable format was nearly impossible due to language-specific scripts, complex multi-column layouts full of entries with abbreviations and cross-references. Recent vision-language models offer a promising solution, but it is unclear how well they preserve characters, markup, and process lexicographic structure. We introduce MUDIDI, a two-stage framework for multi-lingual dictionary digitization. Stage 1 evaluates the quality of character recognition and markup preservation; Stage 2 focuses on dictionary entry segmentation with subsequent mapping into a machine-readable lexicographic schema, SIL’s Multi-Dictionary Formatter. We release a dataset that consists of human-annotated lexicographic entries collected from 30 public-domain dictionaries featuring diverse writing systems, language families, and formats. We benchmark OCR systems, general-purpose Large Language Models (LLMs), and Vision Language Models (VLMs) on the dataset, demonstrating superior performance of LLMs across most writing systems and languages in both stages, and provide practical guidelines on improving the results for more challenging scripts. Finally, we show that supplementing additional information such as dictionary introduction to the LLM can help improve the quality of the digitized dictionary.</abstract>
    <identifier type="citekey">setiawan-etal-2026-mudidi</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2501/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>56806</start>
            <end>56842</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models
%A Setiawan, David Samuel
%A Khishigsuren, Temuulen
%A Agarwal, Milind
%A Pit, Pagnarith
%A Mahmudi, Aso
%A Vylomova, Ekaterina
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F setiawan-etal-2026-mudidi
%X Multilingual dictionaries are among the most valuable documentary resources for low-resource and endangered languages, yet many remain available only as scans. For many decades their digitization and conversion into a machine-readable format was nearly impossible due to language-specific scripts, complex multi-column layouts full of entries with abbreviations and cross-references. Recent vision-language models offer a promising solution, but it is unclear how well they preserve characters, markup, and process lexicographic structure. We introduce MUDIDI, a two-stage framework for multi-lingual dictionary digitization. Stage 1 evaluates the quality of character recognition and markup preservation; Stage 2 focuses on dictionary entry segmentation with subsequent mapping into a machine-readable lexicographic schema, SIL’s Multi-Dictionary Formatter. We release a dataset that consists of human-annotated lexicographic entries collected from 30 public-domain dictionaries featuring diverse writing systems, language families, and formats. We benchmark OCR systems, general-purpose Large Language Models (LLMs), and Vision Language Models (VLMs) on the dataset, demonstrating superior performance of LLMs across most writing systems and languages in both stages, and provide practical guidelines on improving the results for more challenging scripts. Finally, we show that supplementing additional information such as dictionary introduction to the LLM can help improve the quality of the digitized dictionary.
%U https://aclanthology.org/2026.emnlp-main.2501/
%P 56806-56842

Markdown (Informal)

[MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models](https://aclanthology.org/2026.emnlp-main.2501/) (Setiawan et al., EMNLP 2026)

• MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models (Setiawan et al., EMNLP 2026)

ACL

• David Samuel Setiawan, Temuulen Khishigsuren, Milind Agarwal, Pagnarith Pit, Aso Mahmudi, and Ekaterina Vylomova. 2026. MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 56806–56842, Budapest, Hungary. Association for Computational Linguistics.