@inproceedings{he-etal-2023-hauser,
title = "{HAUSER}: Towards Holistic and Automatic Evaluation of Simile Generation",
author = "He, Qianyu and
Zhang, Yikai and
Liang, Jiaqing and
Huang, Yuncheng and
Xiao, Yanghua and
Chen, Yunwen",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.702",
doi = "10.18653/v1/2023.acl-long.702",
pages = "12557--12572",
abstract = "Similes play an imperative role in creative writing such as story and dialogue generation. Proper evaluation metrics are like a beacon guiding the research of simile generation (SG). However, it remains under-explored as to what criteria should be considered, how to quantify each criterion into metrics, and whether the metrics are effective for comprehensive, efficient, and reliable SG evaluation. To address the issues, we establish HAUSER, a holistic and automatic evaluation system for the SG task, which consists of five criteria from three perspectives and automatic metrics for each criterion. Through extensive experiments, we verify that our metrics are significantly more correlated with human ratings from each perspective compared with prior automatic metrics. Resources of HAUSER are publicly available at \url{https://github.com/Abbey4799/HAUSER}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2023-hauser">
<titleInfo>
<title>HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianyu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yikai</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqing</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuncheng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanghua</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunwen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Similes play an imperative role in creative writing such as story and dialogue generation. Proper evaluation metrics are like a beacon guiding the research of simile generation (SG). However, it remains under-explored as to what criteria should be considered, how to quantify each criterion into metrics, and whether the metrics are effective for comprehensive, efficient, and reliable SG evaluation. To address the issues, we establish HAUSER, a holistic and automatic evaluation system for the SG task, which consists of five criteria from three perspectives and automatic metrics for each criterion. Through extensive experiments, we verify that our metrics are significantly more correlated with human ratings from each perspective compared with prior automatic metrics. Resources of HAUSER are publicly available at https://github.com/Abbey4799/HAUSER.</abstract>
<identifier type="citekey">he-etal-2023-hauser</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.702</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.702</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12557</start>
<end>12572</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation
%A He, Qianyu
%A Zhang, Yikai
%A Liang, Jiaqing
%A Huang, Yuncheng
%A Xiao, Yanghua
%A Chen, Yunwen
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F he-etal-2023-hauser
%X Similes play an imperative role in creative writing such as story and dialogue generation. Proper evaluation metrics are like a beacon guiding the research of simile generation (SG). However, it remains under-explored as to what criteria should be considered, how to quantify each criterion into metrics, and whether the metrics are effective for comprehensive, efficient, and reliable SG evaluation. To address the issues, we establish HAUSER, a holistic and automatic evaluation system for the SG task, which consists of five criteria from three perspectives and automatic metrics for each criterion. Through extensive experiments, we verify that our metrics are significantly more correlated with human ratings from each perspective compared with prior automatic metrics. Resources of HAUSER are publicly available at https://github.com/Abbey4799/HAUSER.
%R 10.18653/v1/2023.acl-long.702
%U https://aclanthology.org/2023.acl-long.702
%U https://doi.org/10.18653/v1/2023.acl-long.702
%P 12557-12572
Markdown (Informal)
[HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation](https://aclanthology.org/2023.acl-long.702) (He et al., ACL 2023)
ACL
- Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, and Yunwen Chen. 2023. HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12557–12572, Toronto, Canada. Association for Computational Linguistics.