<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="venturini-etal-2026-talktag">
    <titleInfo>
        <title>TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shamira</namePart>
        <namePart type="family">Venturini</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Oliver</namePart>
        <namePart type="family">Hennhöfer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steffen</namePart>
        <namePart type="family">Kinkel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jannik</namePart>
        <namePart type="family">Strötgen</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 20th Linguistic Annotation Workshop (LAW XX)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="given">Janet</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Luke</namePart>
            <namePart type="family">Gessler</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">979-8-89176-404-0</identifier>
    </relatedItem>
    <abstract>Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation in spoken-language transcripts. Developed under conditions of extreme data scarcity using children’s narrative data, the system shows the feasibility of linguistic analysis in low-resource settings. Our evaluation demonstrates that TalkTag produces encouragingly precise annotation while effectively identifying instances where linguistic ambiguity makes automated tagging genuinely complex. In summary, with TalkTag, we provide a scalable alternative to manual error annotation and practically viable support for morphosyntactic error annotation.</abstract>
    <identifier type="citekey">venturini-etal-2026-talktag</identifier>
    <location>
        <url>https://aclanthology.org/2026.law-main.20/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>309</start>
            <end>322</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech
%A Venturini, Shamira
%A Hennhöfer, Oliver
%A Kinkel, Steffen
%A Strötgen, Jannik
%Y Liu, Yang Janet
%Y Gessler, Luke
%S Proceedings of the 20th Linguistic Annotation Workshop (LAW XX)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-404-0
%F venturini-etal-2026-talktag
%X Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation in spoken-language transcripts. Developed under conditions of extreme data scarcity using children’s narrative data, the system shows the feasibility of linguistic analysis in low-resource settings. Our evaluation demonstrates that TalkTag produces encouragingly precise annotation while effectively identifying instances where linguistic ambiguity makes automated tagging genuinely complex. In summary, with TalkTag, we provide a scalable alternative to manual error annotation and practically viable support for morphosyntactic error annotation.
%U https://aclanthology.org/2026.law-main.20/
%P 309-322

Markdown (Informal)

[TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech](https://aclanthology.org/2026.law-main.20/) (Venturini et al., LAW 2026)

• TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech (Venturini et al., LAW 2026)

ACL

• Shamira Venturini, Oliver Hennhöfer, Steffen Kinkel, and Jannik Strötgen. 2026. TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech. In Proceedings of the 20th Linguistic Annotation Workshop (LAW XX), pages 309–322, San Diego, California, USA. Association for Computational Linguistics.