@inproceedings{lardilleux-lepage-2017-charcut,
title = "{CHARCUT}: Human-Targeted Character-Based {MT} Evaluation with Loose Differences",
author = "Lardilleux, Adrien and
Lepage, Yves",
editor = "Sakti, Sakriani and
Utiyama, Masao",
booktitle = "Proceedings of the 14th International Conference on Spoken Language Translation",
month = dec # " 14-15",
year = "2017",
address = "Tokyo, Japan",
publisher = "International Workshop on Spoken Language Translation",
url = "https://aclanthology.org/2017.iwslt-1.20",
pages = "146--153",
abstract = "We present CHARCUT, a character-based machine translation evaluation metric derived from a human-targeted segment difference visualisation algorithm. It combines an iterative search for longest common substrings between the candidate and the reference translation with a simple length-based threshold, enabling loose differences that limit noisy character matches. Its main advantage is to produce scores that directly reflect human-readable string differences, making it a useful support tool for the manual analysis of MT output and its display to end users. Experiments on WMT16 metrics task data show that it is on par with the best {``}un-trained{''} metrics in terms of correlation with human judgement, well above BLEU and TER baselines, on both system and segment tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lardilleux-lepage-2017-charcut">
<titleInfo>
<title>CHARCUT: Human-Targeted Character-Based MT Evaluation with Loose Differences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adrien</namePart>
<namePart type="family">Lardilleux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Lepage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-dec 14-15</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Spoken Language Translation</title>
</titleInfo>
<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">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Workshop on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present CHARCUT, a character-based machine translation evaluation metric derived from a human-targeted segment difference visualisation algorithm. It combines an iterative search for longest common substrings between the candidate and the reference translation with a simple length-based threshold, enabling loose differences that limit noisy character matches. Its main advantage is to produce scores that directly reflect human-readable string differences, making it a useful support tool for the manual analysis of MT output and its display to end users. Experiments on WMT16 metrics task data show that it is on par with the best “un-trained” metrics in terms of correlation with human judgement, well above BLEU and TER baselines, on both system and segment tasks.</abstract>
<identifier type="citekey">lardilleux-lepage-2017-charcut</identifier>
<location>
<url>https://aclanthology.org/2017.iwslt-1.20</url>
</location>
<part>
<date>2017-dec 14-15</date>
<extent unit="page">
<start>146</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CHARCUT: Human-Targeted Character-Based MT Evaluation with Loose Differences
%A Lardilleux, Adrien
%A Lepage, Yves
%Y Sakti, Sakriani
%Y Utiyama, Masao
%S Proceedings of the 14th International Conference on Spoken Language Translation
%D 2017
%8 dec 14 15
%I International Workshop on Spoken Language Translation
%C Tokyo, Japan
%F lardilleux-lepage-2017-charcut
%X We present CHARCUT, a character-based machine translation evaluation metric derived from a human-targeted segment difference visualisation algorithm. It combines an iterative search for longest common substrings between the candidate and the reference translation with a simple length-based threshold, enabling loose differences that limit noisy character matches. Its main advantage is to produce scores that directly reflect human-readable string differences, making it a useful support tool for the manual analysis of MT output and its display to end users. Experiments on WMT16 metrics task data show that it is on par with the best “un-trained” metrics in terms of correlation with human judgement, well above BLEU and TER baselines, on both system and segment tasks.
%U https://aclanthology.org/2017.iwslt-1.20
%P 146-153
Markdown (Informal)
[CHARCUT: Human-Targeted Character-Based MT Evaluation with Loose Differences](https://aclanthology.org/2017.iwslt-1.20) (Lardilleux & Lepage, IWSLT 2017)
ACL