@inproceedings{guan-etal-2021-openmeva,
title = "{O}pen{MEVA}: A Benchmark for Evaluating Open-ended Story Generation Metrics",
author = "Guan, Jian and
Zhang, Zhexin and
Feng, Zhuoer and
Liu, Zitao and
Ding, Wenbiao and
Mao, Xiaoxi and
Fan, Changjie and
Huang, Minlie",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.500/",
doi = "10.18653/v1/2021.acl-long.500",
pages = "6394--6407",
abstract = "Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation. However, existing automatic metrics are observed to correlate poorly with human evaluation. The lack of standardized benchmark datasets makes it difficult to fully evaluate the capabilities of a metric and fairly compare different metrics. Therefore, we propose OpenMEVA, a benchmark for evaluating open-ended story generation metrics. OpenMEVA provides a comprehensive test suite to assess the capabilities of metrics, including (a) the correlation with human judgments, (b) the generalization to different model outputs and datasets, (c) the ability to judge story coherence, and (d) the robustness to perturbations. To this end, OpenMEVA includes both manually annotated stories and auto-constructed test examples. We evaluate existing metrics on OpenMEVA and observe that they have poor correlation with human judgments, fail to recognize discourse-level incoherence, and lack inferential knowledge (e.g., causal order between events), the generalization ability and robustness. Our study presents insights for developing NLG models and metrics in further research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-etal-2021-openmeva">
<titleInfo>
<title>OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhexin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuoer</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zitao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbiao</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxi</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changjie</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minlie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation. However, existing automatic metrics are observed to correlate poorly with human evaluation. The lack of standardized benchmark datasets makes it difficult to fully evaluate the capabilities of a metric and fairly compare different metrics. Therefore, we propose OpenMEVA, a benchmark for evaluating open-ended story generation metrics. OpenMEVA provides a comprehensive test suite to assess the capabilities of metrics, including (a) the correlation with human judgments, (b) the generalization to different model outputs and datasets, (c) the ability to judge story coherence, and (d) the robustness to perturbations. To this end, OpenMEVA includes both manually annotated stories and auto-constructed test examples. We evaluate existing metrics on OpenMEVA and observe that they have poor correlation with human judgments, fail to recognize discourse-level incoherence, and lack inferential knowledge (e.g., causal order between events), the generalization ability and robustness. Our study presents insights for developing NLG models and metrics in further research.</abstract>
<identifier type="citekey">guan-etal-2021-openmeva</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.500</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.500/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>6394</start>
<end>6407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics
%A Guan, Jian
%A Zhang, Zhexin
%A Feng, Zhuoer
%A Liu, Zitao
%A Ding, Wenbiao
%A Mao, Xiaoxi
%A Fan, Changjie
%A Huang, Minlie
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F guan-etal-2021-openmeva
%X Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation. However, existing automatic metrics are observed to correlate poorly with human evaluation. The lack of standardized benchmark datasets makes it difficult to fully evaluate the capabilities of a metric and fairly compare different metrics. Therefore, we propose OpenMEVA, a benchmark for evaluating open-ended story generation metrics. OpenMEVA provides a comprehensive test suite to assess the capabilities of metrics, including (a) the correlation with human judgments, (b) the generalization to different model outputs and datasets, (c) the ability to judge story coherence, and (d) the robustness to perturbations. To this end, OpenMEVA includes both manually annotated stories and auto-constructed test examples. We evaluate existing metrics on OpenMEVA and observe that they have poor correlation with human judgments, fail to recognize discourse-level incoherence, and lack inferential knowledge (e.g., causal order between events), the generalization ability and robustness. Our study presents insights for developing NLG models and metrics in further research.
%R 10.18653/v1/2021.acl-long.500
%U https://aclanthology.org/2021.acl-long.500/
%U https://doi.org/10.18653/v1/2021.acl-long.500
%P 6394-6407
Markdown (Informal)
[OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics](https://aclanthology.org/2021.acl-long.500/) (Guan et al., ACL-IJCNLP 2021)
ACL
- Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, and Minlie Huang. 2021. OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6394–6407, Online. Association for Computational Linguistics.