@inproceedings{lorandi-belz-2024-reproducing,
title = "Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques",
author = "Lorandi, Michela and
Belz, Anya",
editor = "Balloccu, Simone and
Belz, Anya and
Huidrom, Rudali and
Reiter, Ehud and
Sedoc, Joao and
Thomson, Craig",
booktitle = "Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.humeval-1.12/",
pages = "125--131",
abstract = "Rerunning a metric-based evaluation should be more straightforward and results should be closer than in a human-based evaluation, especially where code and model checkpoints are made available by the original authors. As this brief report of our efforts to rerun a metric-based evaluation of a set of multi-aspect controllable text generation (CTG) techniques shows however, such reruns of evaluations do not always produce results that are the same as the original results, and can reveal errors in the orginal work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lorandi-belz-2024-reproducing">
<titleInfo>
<title>Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michela</namePart>
<namePart type="family">Lorandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</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 Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Balloccu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudali</namePart>
<namePart type="family">Huidrom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Thomson</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>Rerunning a metric-based evaluation should be more straightforward and results should be closer than in a human-based evaluation, especially where code and model checkpoints are made available by the original authors. As this brief report of our efforts to rerun a metric-based evaluation of a set of multi-aspect controllable text generation (CTG) techniques shows however, such reruns of evaluations do not always produce results that are the same as the original results, and can reveal errors in the orginal work.</abstract>
<identifier type="citekey">lorandi-belz-2024-reproducing</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.12/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>125</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques
%A Lorandi, Michela
%A Belz, Anya
%Y Balloccu, Simone
%Y Belz, Anya
%Y Huidrom, Rudali
%Y Reiter, Ehud
%Y Sedoc, Joao
%Y Thomson, Craig
%S Proceedings of the Fourth Workshop on Human Evaluation of NLP Systems (HumEval) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lorandi-belz-2024-reproducing
%X Rerunning a metric-based evaluation should be more straightforward and results should be closer than in a human-based evaluation, especially where code and model checkpoints are made available by the original authors. As this brief report of our efforts to rerun a metric-based evaluation of a set of multi-aspect controllable text generation (CTG) techniques shows however, such reruns of evaluations do not always produce results that are the same as the original results, and can reveal errors in the orginal work.
%U https://aclanthology.org/2024.humeval-1.12/
%P 125-131
Markdown (Informal)
[Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques](https://aclanthology.org/2024.humeval-1.12/) (Lorandi & Belz, HumEval 2024)
ACL