@inproceedings{karakanta-etal-2024-evaluating-automatic,
title = "Evaluating Automatic Subtitling: Correlating Post-editing Effort and Automatic Metrics",
author = "Karakanta, Alina and
Cettolo, Mauro and
Negri, Matteo and
Bentivogli, Luisa",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.563",
pages = "6363--6369",
abstract = "Systems that automatically generate subtitles from video are gradually entering subtitling workflows, both for supporting subtitlers and for accessibility purposes. Even though robust metrics are essential for evaluating the quality of automatically-generated subtitles and for estimating potential productivity gains, there is limited research on whether existing metrics, some of which directly borrowed from machine translation (MT) evaluation, can fulfil such purposes. This paper investigates how well such MT metrics correlate with measures of post-editing (PE) effort in automatic subtitling. To this aim, we collect and publicly release a new corpus containing product-, process- and participant-based data from post-editing automatic subtitles in two language pairs (en→de,it). We find that different types of metrics correlate with different aspects of PE effort. Specifically, edit distance metrics have high correlation with technical and temporal effort, while neural metrics correlate well with PE speed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karakanta-etal-2024-evaluating-automatic">
<titleInfo>
<title>Evaluating Automatic Subtitling: Correlating Post-editing Effort and Automatic Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Systems that automatically generate subtitles from video are gradually entering subtitling workflows, both for supporting subtitlers and for accessibility purposes. Even though robust metrics are essential for evaluating the quality of automatically-generated subtitles and for estimating potential productivity gains, there is limited research on whether existing metrics, some of which directly borrowed from machine translation (MT) evaluation, can fulfil such purposes. This paper investigates how well such MT metrics correlate with measures of post-editing (PE) effort in automatic subtitling. To this aim, we collect and publicly release a new corpus containing product-, process- and participant-based data from post-editing automatic subtitles in two language pairs (en→de,it). We find that different types of metrics correlate with different aspects of PE effort. Specifically, edit distance metrics have high correlation with technical and temporal effort, while neural metrics correlate well with PE speed.</abstract>
<identifier type="citekey">karakanta-etal-2024-evaluating-automatic</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.563</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6363</start>
<end>6369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Automatic Subtitling: Correlating Post-editing Effort and Automatic Metrics
%A Karakanta, Alina
%A Cettolo, Mauro
%A Negri, Matteo
%A Bentivogli, Luisa
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F karakanta-etal-2024-evaluating-automatic
%X Systems that automatically generate subtitles from video are gradually entering subtitling workflows, both for supporting subtitlers and for accessibility purposes. Even though robust metrics are essential for evaluating the quality of automatically-generated subtitles and for estimating potential productivity gains, there is limited research on whether existing metrics, some of which directly borrowed from machine translation (MT) evaluation, can fulfil such purposes. This paper investigates how well such MT metrics correlate with measures of post-editing (PE) effort in automatic subtitling. To this aim, we collect and publicly release a new corpus containing product-, process- and participant-based data from post-editing automatic subtitles in two language pairs (en→de,it). We find that different types of metrics correlate with different aspects of PE effort. Specifically, edit distance metrics have high correlation with technical and temporal effort, while neural metrics correlate well with PE speed.
%U https://aclanthology.org/2024.lrec-main.563
%P 6363-6369
Markdown (Informal)
[Evaluating Automatic Subtitling: Correlating Post-editing Effort and Automatic Metrics](https://aclanthology.org/2024.lrec-main.563) (Karakanta et al., LREC-COLING 2024)
ACL