<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maracani-etal-2026-decoding">
    <titleInfo>
        <title>Decoding Text Spans for Efficient and Accurate Named-Entity Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Maracani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Savas</namePart>
        <namePart type="family">Ozkan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junyi</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sinan</namePart>
        <namePart type="family">Mutlu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mete</namePart>
        <namePart type="family">Ozay</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 (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Georg</namePart>
            <namePart type="family">Rehm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mei</namePart>
            <namePart type="family">Tu</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, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-394-4</identifier>
    </relatedItem>
    <abstract>Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often achieved by span-based frameworks, which construct span representations from token encodings and classify candidate spans. However, many span-based methods enumerate large numbers of candidates and process each candidate with marker-augmented inputs, substantially increasing inference cost and limiting scalability in large-scale deployments. In this work, we propose SpanDec, an efficient span-based NER framework that targets this bottleneck. Our main insight is that span representation interactions can be computed effectively at the final transformer stage, avoiding redundant computation in earlier layers via a lightweight decoder dedicated to span representations. We further introduce a span filtering mechanism during enumeration to prune unlikely candidates before expensive processing. Across multiple benchmarks, SpanDec matches competitive span-based baselines while improving throughput and reducing computational cost, yielding a better accuracy–efficiency trade-off suitable for high-volume serving and on-device applications.</abstract>
    <identifier type="citekey">maracani-etal-2026-decoding</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-industry.71/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1025</start>
            <end>1036</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Decoding Text Spans for Efficient and Accurate Named-Entity Recognition
%A Maracani, Andrea
%A Ozkan, Savas
%A Zhu, Junyi
%A Mutlu, Sinan
%A Ozay, Mete
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F maracani-etal-2026-decoding
%X Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often achieved by span-based frameworks, which construct span representations from token encodings and classify candidate spans. However, many span-based methods enumerate large numbers of candidates and process each candidate with marker-augmented inputs, substantially increasing inference cost and limiting scalability in large-scale deployments. In this work, we propose SpanDec, an efficient span-based NER framework that targets this bottleneck. Our main insight is that span representation interactions can be computed effectively at the final transformer stage, avoiding redundant computation in earlier layers via a lightweight decoder dedicated to span representations. We further introduce a span filtering mechanism during enumeration to prune unlikely candidates before expensive processing. Across multiple benchmarks, SpanDec matches competitive span-based baselines while improving throughput and reducing computational cost, yielding a better accuracy–efficiency trade-off suitable for high-volume serving and on-device applications.
%U https://aclanthology.org/2026.acl-industry.71/
%P 1025-1036

Markdown (Informal)

[Decoding Text Spans for Efficient and Accurate Named-Entity Recognition](https://aclanthology.org/2026.acl-industry.71/) (Maracani et al., ACL 2026)

• Decoding Text Spans for Efficient and Accurate Named-Entity Recognition (Maracani et al., ACL 2026)

ACL

• Andrea Maracani, Savas Ozkan, Junyi Zhu, Sinan Mutlu, and Mete Ozay. 2026. Decoding Text Spans for Efficient and Accurate Named-Entity Recognition. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1025–1036, San Diego, California, USA. Association for Computational Linguistics.