@inproceedings{arvan-parde-2024-reprohum,
title = "{R}epro{H}um {\#}0712-01: Human Evaluation Reproduction Report for {\textquotedblleft}Hierarchical Sketch Induction for Paraphrase Generation{\textquotedblright}",
author = "Arvan, Mohammad and
Parde, Natalie",
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-1.18/",
pages = "210--220",
abstract = "Human evaluations are indispensable in the development of NLP systems because they provide direct insights into how effectively these systems meet real-world needs and expectations. Ensuring the reproducibility of these evaluations is vital for maintaining credibility in natural language processing research. This paper presents our reproduction of the human evaluation experiments conducted by Hosking et al. (2022) for their paraphrase generation approach. Through careful replication we found that our results closely align with those in the original study, indicating a high degree of reproducibility."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arvan-parde-2024-reprohum">
<titleInfo>
<title>ReproHum #0712-01: Human Evaluation Reproduction Report for “Hierarchical Sketch Induction for Paraphrase Generation”</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Arvan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</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>Human evaluations are indispensable in the development of NLP systems because they provide direct insights into how effectively these systems meet real-world needs and expectations. Ensuring the reproducibility of these evaluations is vital for maintaining credibility in natural language processing research. This paper presents our reproduction of the human evaluation experiments conducted by Hosking et al. (2022) for their paraphrase generation approach. Through careful replication we found that our results closely align with those in the original study, indicating a high degree of reproducibility.</abstract>
<identifier type="citekey">arvan-parde-2024-reprohum</identifier>
<location>
<url>https://aclanthology.org/2024.humeval-1.18/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>210</start>
<end>220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReproHum #0712-01: Human Evaluation Reproduction Report for “Hierarchical Sketch Induction for Paraphrase Generation”
%A Arvan, Mohammad
%A Parde, Natalie
%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 arvan-parde-2024-reprohum
%X Human evaluations are indispensable in the development of NLP systems because they provide direct insights into how effectively these systems meet real-world needs and expectations. Ensuring the reproducibility of these evaluations is vital for maintaining credibility in natural language processing research. This paper presents our reproduction of the human evaluation experiments conducted by Hosking et al. (2022) for their paraphrase generation approach. Through careful replication we found that our results closely align with those in the original study, indicating a high degree of reproducibility.
%U https://aclanthology.org/2024.humeval-1.18/
%P 210-220
Markdown (Informal)
[ReproHum #0712-01: Human Evaluation Reproduction Report for “Hierarchical Sketch Induction for Paraphrase Generation”](https://aclanthology.org/2024.humeval-1.18/) (Arvan & Parde, HumEval 2024)
ACL