@inproceedings{yi-etal-2020-improving,
title = "Improving Image Captioning Evaluation by Considering Inter References Variance",
author = "Yi, Yanzhi and
Deng, Hangyu and
Hu, Jinglu",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.93/",
doi = "10.18653/v1/2020.acl-main.93",
pages = "985--994",
abstract = "Evaluating image captions is very challenging partially due to the fact that there are multiple correct captions for every single image. Most of the existing one-to-one metrics operate by penalizing mismatches between reference and generative caption without considering the intrinsic variance between ground truth captions. It usually leads to over-penalization and thus a bad correlation to human judgment. Recently, the latest one-to-one metric BERTScore can achieve high human correlation in system-level tasks while some issues can be fixed for better performance. In this paper, we propose a novel metric based on BERTScore that could handle such a challenge and extend BERTScore with a few new features appropriately for image captioning evaluation. The experimental results show that our metric achieves state-of-the-art human judgment correlation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yi-etal-2020-improving">
<titleInfo>
<title>Improving Image Captioning Evaluation by Considering Inter References Variance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanzhi</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hangyu</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinglu</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>Evaluating image captions is very challenging partially due to the fact that there are multiple correct captions for every single image. Most of the existing one-to-one metrics operate by penalizing mismatches between reference and generative caption without considering the intrinsic variance between ground truth captions. It usually leads to over-penalization and thus a bad correlation to human judgment. Recently, the latest one-to-one metric BERTScore can achieve high human correlation in system-level tasks while some issues can be fixed for better performance. In this paper, we propose a novel metric based on BERTScore that could handle such a challenge and extend BERTScore with a few new features appropriately for image captioning evaluation. The experimental results show that our metric achieves state-of-the-art human judgment correlation.</abstract>
<identifier type="citekey">yi-etal-2020-improving</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.93</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.93/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>985</start>
<end>994</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Image Captioning Evaluation by Considering Inter References Variance
%A Yi, Yanzhi
%A Deng, Hangyu
%A Hu, Jinglu
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F yi-etal-2020-improving
%X Evaluating image captions is very challenging partially due to the fact that there are multiple correct captions for every single image. Most of the existing one-to-one metrics operate by penalizing mismatches between reference and generative caption without considering the intrinsic variance between ground truth captions. It usually leads to over-penalization and thus a bad correlation to human judgment. Recently, the latest one-to-one metric BERTScore can achieve high human correlation in system-level tasks while some issues can be fixed for better performance. In this paper, we propose a novel metric based on BERTScore that could handle such a challenge and extend BERTScore with a few new features appropriately for image captioning evaluation. The experimental results show that our metric achieves state-of-the-art human judgment correlation.
%R 10.18653/v1/2020.acl-main.93
%U https://aclanthology.org/2020.acl-main.93/
%U https://doi.org/10.18653/v1/2020.acl-main.93
%P 985-994
Markdown (Informal)
[Improving Image Captioning Evaluation by Considering Inter References Variance](https://aclanthology.org/2020.acl-main.93/) (Yi et al., ACL 2020)
ACL