<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ray-etal-2026-diffnectis">
    <titleInfo>
        <title>DiffNeCTIS: Diffusion-based Nested Compound Type Identification for Sanskrit</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pretam</namePart>
        <namePart type="family">Ray</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sinchani</namePart>
        <namePart type="family">Chakraborty</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sriram</namePart>
        <namePart type="family">Krishnan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Manoj</namePart>
        <namePart type="given">Balaji</namePart>
        <namePart type="family">Jagadeeshan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pawan</namePart>
        <namePart type="family">Goyal</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>Sanskrit multi-component compounding presents a severe structured prediction challenge: the space of valid parse structures grows exponentially with compound length, implicit semantic relations are highly context-sensitive, and accurate type assignment demands simultaneous global structural coherence and local morphological precision across a fine-grained label typology. Existing systems address Nested Compound Type Identification for Sanskrit (NeCTIS) discriminatively, predicting dependency edges and semantic types in a single greedy pass. Reformulating NeCTIS as iterative generative refinement via diffusion over the full label sequence resolves this structural inconsistency but exposes a complementary bottleneck - coarse global attention that suppresses the localized morphological signals necessary for fine-grained type discrimination. We address this through a local refinement mechanism within a restricted window.\par We further provide the first systematic evaluation of large language models on NeCTIS, finding consistent and substantial failures under zero-shot and few-shot conditions - attributable to the absence of structural inductive biases, Sanskrit under-representation in pretraining, and morphological sensitivity requirements that broad-coverage models are fundamentally ill-equipped to satisfy.</abstract>
    <identifier type="citekey">ray-etal-2026-diffnectis</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2378/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>54021</start>
            <end>54039</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DiffNeCTIS: Diffusion-based Nested Compound Type Identification for Sanskrit
%A Ray, Pretam
%A Chakraborty, Sinchani
%A Krishnan, Sriram
%A Jagadeeshan, Manoj Balaji
%A Goyal, Pawan
%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 ray-etal-2026-diffnectis
%X Sanskrit multi-component compounding presents a severe structured prediction challenge: the space of valid parse structures grows exponentially with compound length, implicit semantic relations are highly context-sensitive, and accurate type assignment demands simultaneous global structural coherence and local morphological precision across a fine-grained label typology. Existing systems address Nested Compound Type Identification for Sanskrit (NeCTIS) discriminatively, predicting dependency edges and semantic types in a single greedy pass. Reformulating NeCTIS as iterative generative refinement via diffusion over the full label sequence resolves this structural inconsistency but exposes a complementary bottleneck - coarse global attention that suppresses the localized morphological signals necessary for fine-grained type discrimination. We address this through a local refinement mechanism within a restricted window.\par We further provide the first systematic evaluation of large language models on NeCTIS, finding consistent and substantial failures under zero-shot and few-shot conditions - attributable to the absence of structural inductive biases, Sanskrit under-representation in pretraining, and morphological sensitivity requirements that broad-coverage models are fundamentally ill-equipped to satisfy.
%U https://aclanthology.org/2026.emnlp-main.2378/
%P 54021-54039

Markdown (Informal)

[DiffNeCTIS: Diffusion-based Nested Compound Type Identification for Sanskrit](https://aclanthology.org/2026.emnlp-main.2378/) (Ray et al., EMNLP 2026)

• DiffNeCTIS: Diffusion-based Nested Compound Type Identification for Sanskrit (Ray et al., EMNLP 2026)

ACL

• Pretam Ray, Sinchani Chakraborty, Sriram Krishnan, Manoj Balaji Jagadeeshan, and Pawan Goyal. 2026. DiffNeCTIS: Diffusion-based Nested Compound Type Identification for Sanskrit. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 54021–54039, Budapest, Hungary. Association for Computational Linguistics.