<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kellert-etal-2025-parsing">
    <titleInfo>
        <title>Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Olga</namePart>
        <namePart type="family">Kellert</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nemika</namePart>
        <namePart type="family">Tyagi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="family">Imran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nelvin</namePart>
        <namePart type="family">Licona-Guevara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carlos</namePart>
        <namePart type="family">Gómez-Rodríguez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>Code-switching presents a complex challenge for syntactic analysis, especially in low-resource language settings where annotated data is scarce. While recent work has explored the use of large language models (LLMs) for sequence-level tagging, few approaches systematically investigate how well these models capture syntactic structure in code-switched contexts. Moreover, existing parsers trained on monolingual treebanks often fail to generalize to multilingual and mixed-language input. To address this gap, we introduce the BiLingua Pipeline, an LLM-based annotation pipeline designed to produce Universal Dependencies (UD) annotations for code-switched text. First, we develop a prompt-based framework for Spanish-English and Spanish-Guaraní data, combining few-shot LLM prompting with expert review. Second, we release two annotated datasets, including the first Spanish-Guaraní UD-parsed corpus. Third, we conduct a detailed syntactic analysis of switch points across language pairs and communicative contexts. Experimental results show that BiLingua Pipeline achieves up to 95.29% LAS after expert revision, significantly outperforming prior baselines and multilingual parsers. These results show that LLMs, when carefully guided, can serve as practical tools for bootstrapping syntactic resources in under-resourced, code-switched environments.</abstract>
    <identifier type="citekey">kellert-etal-2025-parsing</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.863/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>15934</start>
            <end>15949</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages
%A Kellert, Olga
%A Tyagi, Nemika
%A Imran, Muhammad
%A Licona-Guevara, Nelvin
%A Gómez-Rodríguez, Carlos
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F kellert-etal-2025-parsing
%X Code-switching presents a complex challenge for syntactic analysis, especially in low-resource language settings where annotated data is scarce. While recent work has explored the use of large language models (LLMs) for sequence-level tagging, few approaches systematically investigate how well these models capture syntactic structure in code-switched contexts. Moreover, existing parsers trained on monolingual treebanks often fail to generalize to multilingual and mixed-language input. To address this gap, we introduce the BiLingua Pipeline, an LLM-based annotation pipeline designed to produce Universal Dependencies (UD) annotations for code-switched text. First, we develop a prompt-based framework for Spanish-English and Spanish-Guaraní data, combining few-shot LLM prompting with expert review. Second, we release two annotated datasets, including the first Spanish-Guaraní UD-parsed corpus. Third, we conduct a detailed syntactic analysis of switch points across language pairs and communicative contexts. Experimental results show that BiLingua Pipeline achieves up to 95.29% LAS after expert revision, significantly outperforming prior baselines and multilingual parsers. These results show that LLMs, when carefully guided, can serve as practical tools for bootstrapping syntactic resources in under-resourced, code-switched environments.
%U https://aclanthology.org/2025.findings-emnlp.863/
%P 15934-15949

Markdown (Informal)

[Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages](https://aclanthology.org/2025.findings-emnlp.863/) (Kellert et al., Findings 2025)

• Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages (Kellert et al., Findings 2025)

ACL

• Olga Kellert, Nemika Tyagi, Muhammad Imran, Nelvin Licona-Guevara, and Carlos Gómez-Rodríguez. 2025. Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15934–15949, Suzhou, China. Association for Computational Linguistics.