<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dewangan-maurya-2026-claocs">
    <titleInfo>
        <title>CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lipika</namePart>
        <namePart type="family">Dewangan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chandresh</namePart>
        <namePart type="given">Kumar</namePart>
        <namePart type="family">Maurya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Cross-lingual learning enables the transfer of structured sentiment knowledge from high-resource languages to unlabeled or low-resource languages, but prior work has largely focused on coarse-grained sentiment classification or aspect extraction. In contrast, zero-shot cross-lingual aspect–opinion–sentiment triplet extraction (ASTE), which extracts sentiment triplets of the form (aspect term, opinion term, sentiment polarity), remains underexplored. We propose a unified framework that leverages large language models (LLMs) as both structured pseudo-label generators and semantic teachers for ASTE. Our approach employs stepwise structured prompting over aspect- and opinion-aware code-switched variants to generate reliable pseudo triplets, followed by a multi-variant consistency filter to retain high-confidence supervision. We further introduce a triplet-aware contrastive distillation objective that aligns student triplet representations with LLM-encoded semantic embeddings. During inference, only the student ASTE model is used, without requiring LLM access. Experiments on four non-Indic and four low-resource Indic target languages show consistent improvements over strong cross-lingual and LLM-based baselines. The proposed method yields an absolute micro-F1 improvement of 5.3 points on non-Indic languages and 3.8 points on low-resource Indic languages compared to the best competing approach. Ablation results further validate the complementary roles of aspect- and opinion-aware code-switched prompting and triplet-aware contrastive distillation, with larger relative gains observed in low-resource Indic settings.</abstract>
    <identifier type="citekey">dewangan-maurya-2026-claocs</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.2063/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>44561</start>
            <end>44577</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation
%A Dewangan, Lipika
%A Maurya, Chandresh Kumar
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F dewangan-maurya-2026-claocs
%X Cross-lingual learning enables the transfer of structured sentiment knowledge from high-resource languages to unlabeled or low-resource languages, but prior work has largely focused on coarse-grained sentiment classification or aspect extraction. In contrast, zero-shot cross-lingual aspect–opinion–sentiment triplet extraction (ASTE), which extracts sentiment triplets of the form (aspect term, opinion term, sentiment polarity), remains underexplored. We propose a unified framework that leverages large language models (LLMs) as both structured pseudo-label generators and semantic teachers for ASTE. Our approach employs stepwise structured prompting over aspect- and opinion-aware code-switched variants to generate reliable pseudo triplets, followed by a multi-variant consistency filter to retain high-confidence supervision. We further introduce a triplet-aware contrastive distillation objective that aligns student triplet representations with LLM-encoded semantic embeddings. During inference, only the student ASTE model is used, without requiring LLM access. Experiments on four non-Indic and four low-resource Indic target languages show consistent improvements over strong cross-lingual and LLM-based baselines. The proposed method yields an absolute micro-F1 improvement of 5.3 points on non-Indic languages and 3.8 points on low-resource Indic languages compared to the best competing approach. Ablation results further validate the complementary roles of aspect- and opinion-aware code-switched prompting and triplet-aware contrastive distillation, with larger relative gains observed in low-resource Indic settings.
%U https://aclanthology.org/2026.acl-long.2063/
%P 44561-44577

Markdown (Informal)

[CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation](https://aclanthology.org/2026.acl-long.2063/) (Dewangan & Maurya, ACL 2026)

• CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation (Dewangan & Maurya, ACL 2026)

ACL

• Lipika Dewangan and Chandresh Kumar Maurya. 2026. CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 44561–44577, San Diego, California, United States. Association for Computational Linguistics.