<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vedula-etal-2026-scaling">
    <titleInfo>
        <title>Scaling E-Commerce Attribute Extraction with Parallel Decoding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nikhita</namePart>
        <namePart type="family">Vedula</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dushyanta</namePart>
        <namePart type="family">Dhyani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bryan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shervin</namePart>
        <namePart type="family">Malmasi</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 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jan-Christoph</namePart>
            <namePart type="family">Kalo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ndapa</namePart>
            <namePart type="family">Nakashole</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Razniewski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fabian</namePart>
            <namePart type="given">M</namePart>
            <namePart type="family">Suchanek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andrew</namePart>
            <namePart type="family">McCallum</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">979-8-89176-464-4</identifier>
    </relatedItem>
    <abstract>Customers rely on specific product attributes to compare products and make purchasing decisions, but E-Commerce catalogs are messy and unstructured, making it difficult to identify which attributes matter most and extract them at scale. Standard Attribute Value Extraction (AVE) systems treat all attributes equally, producing large, inconsistent attribute sets that do not reflect the factors consumers use to differentiate products. We introduce a two-stage LLM pipeline that first discovers a compact, ranked schema of purchase-discriminative attributes for each product category, then extracts their values from catalog text using a fine-tuned compact LLM (Qwen3-4B) with Hyper-Parallel Decoding (HPD). This pipeline achieves 85% extraction accuracy, on par with the foundational LLM it was trained on, while reducing inference costs by 92% over foundational LLMs, enabling production-scale use for product discovery and catalog enrichment. The resulting category-level structured representations effectively constitute automatically constructed product knowledge bases, providing consistent, comparable attributes across varied product categories that can ground downstream knowledge-intensive applications.</abstract>
    <identifier type="citekey">vedula-etal-2026-scaling</identifier>
    <location>
        <url>https://aclanthology.org/2026.akbc-1.13/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>169</start>
            <end>177</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Scaling E-Commerce Attribute Extraction with Parallel Decoding
%A Vedula, Nikhita
%A Dhyani, Dushyanta
%A Wang, Bryan
%A Malmasi, Shervin
%Y Kalo, Jan-Christoph
%Y Nakashole, Ndapa
%Y Razniewski, Simon
%Y Suchanek, Fabian M.
%Y Vlachos, Andreas
%Y McCallum, Andrew
%S Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-464-4
%F vedula-etal-2026-scaling
%X Customers rely on specific product attributes to compare products and make purchasing decisions, but E-Commerce catalogs are messy and unstructured, making it difficult to identify which attributes matter most and extract them at scale. Standard Attribute Value Extraction (AVE) systems treat all attributes equally, producing large, inconsistent attribute sets that do not reflect the factors consumers use to differentiate products. We introduce a two-stage LLM pipeline that first discovers a compact, ranked schema of purchase-discriminative attributes for each product category, then extracts their values from catalog text using a fine-tuned compact LLM (Qwen3-4B) with Hyper-Parallel Decoding (HPD). This pipeline achieves 85% extraction accuracy, on par with the foundational LLM it was trained on, while reducing inference costs by 92% over foundational LLMs, enabling production-scale use for product discovery and catalog enrichment. The resulting category-level structured representations effectively constitute automatically constructed product knowledge bases, providing consistent, comparable attributes across varied product categories that can ground downstream knowledge-intensive applications.
%U https://aclanthology.org/2026.akbc-1.13/
%P 169-177

Markdown (Informal)

[Scaling E-Commerce Attribute Extraction with Parallel Decoding](https://aclanthology.org/2026.akbc-1.13/) (Vedula et al., AKBC 2026)

• Scaling E-Commerce Attribute Extraction with Parallel Decoding (Vedula et al., AKBC 2026)

ACL

• Nikhita Vedula, Dushyanta Dhyani, Bryan Wang, and Shervin Malmasi. 2026. Scaling E-Commerce Attribute Extraction with Parallel Decoding. In Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), pages 169–177, Budapest, Hungary. Association for Computational Linguistics.