@inproceedings{mechler-etal-2026-transcription,
title = "Transcription Accuracy in the {I}celandic {G}igaword Corpus: Evaluating Automatic and Manual Annotation",
author = {Mechler, Johanna and
Stef{\'a}nsd{\'o}ttir, Lilja Bj{\"o}rk and
Ingason, Anton Karl},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.373/",
doi = "10.63317/4f2rpzig5h8p",
pages = "4757--4764",
abstract = "This paper aims to compare automatic and manually corrected annotation data in the Icelandic Gigaword Corpus. We focus on the variable use of Stylistic Fronting (SF) in Icelandic, an optional movement of words or phrases, which indicates a more formal style. Examining SF rates across time, we find that manual coding results in slightly lower SF rates than automatic coding. This difference can be explained by the different sources used in the coding process: For automatic coding, written transcripts compiled by parliament employees are used, and for manual correction, coding relies on audio files of the parliament speeches. Importantly, both types of coding are well suited to trace changing patterns of SF over a span of 16 years, suggesting that the automatic feature extraction reliably reflects the speeches that have been transcribed."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mechler-etal-2026-transcription">
<titleInfo>
<title>Transcription Accuracy in the Icelandic Gigaword Corpus: Evaluating Automatic and Manual Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Mechler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="given">Björk</namePart>
<namePart type="family">Stefánsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="given">Karl</namePart>
<namePart type="family">Ingason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper aims to compare automatic and manually corrected annotation data in the Icelandic Gigaword Corpus. We focus on the variable use of Stylistic Fronting (SF) in Icelandic, an optional movement of words or phrases, which indicates a more formal style. Examining SF rates across time, we find that manual coding results in slightly lower SF rates than automatic coding. This difference can be explained by the different sources used in the coding process: For automatic coding, written transcripts compiled by parliament employees are used, and for manual correction, coding relies on audio files of the parliament speeches. Importantly, both types of coding are well suited to trace changing patterns of SF over a span of 16 years, suggesting that the automatic feature extraction reliably reflects the speeches that have been transcribed.</abstract>
<identifier type="citekey">mechler-etal-2026-transcription</identifier>
<identifier type="doi">10.63317/4f2rpzig5h8p</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.373/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4757</start>
<end>4764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transcription Accuracy in the Icelandic Gigaword Corpus: Evaluating Automatic and Manual Annotation
%A Mechler, Johanna
%A Stefánsdóttir, Lilja Björk
%A Ingason, Anton Karl
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F mechler-etal-2026-transcription
%X This paper aims to compare automatic and manually corrected annotation data in the Icelandic Gigaword Corpus. We focus on the variable use of Stylistic Fronting (SF) in Icelandic, an optional movement of words or phrases, which indicates a more formal style. Examining SF rates across time, we find that manual coding results in slightly lower SF rates than automatic coding. This difference can be explained by the different sources used in the coding process: For automatic coding, written transcripts compiled by parliament employees are used, and for manual correction, coding relies on audio files of the parliament speeches. Importantly, both types of coding are well suited to trace changing patterns of SF over a span of 16 years, suggesting that the automatic feature extraction reliably reflects the speeches that have been transcribed.
%R 10.63317/4f2rpzig5h8p
%U https://aclanthology.org/2026.lrec-1.373/
%U https://doi.org/10.63317/4f2rpzig5h8p
%P 4757-4764
Markdown (Informal)
[Transcription Accuracy in the Icelandic Gigaword Corpus: Evaluating Automatic and Manual Annotation](https://aclanthology.org/2026.lrec-1.373/) (Mechler et al., LREC 2026)
ACL