@inproceedings{shi-etal-2021-enhancing,
title = "Enhancing Descriptive Image Captioning with Natural Language Inference",
author = "Shi, Zhan and
Liu, Hui and
Zhu, Xiaodan",
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 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.36/",
doi = "10.18653/v1/2021.acl-short.36",
pages = "269--277",
abstract = "Generating \textit{descriptive} sentences that convey non-trivial, detailed, and salient information about images is an important goal of image captioning. In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions. Specifically, we construct directed inference graphs for reference captions based on natural language inference. A PageRank algorithm is then employed to estimate the descriptiveness score of each node. Built on that, we use reference sampling and weighted designated rewards to guide captioning to generate descriptive captions. The results on MSCOCO show that the proposed method outperforms the baselines significantly on a wide range of conventional and descriptiveness-related evaluation metrics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2021-enhancing">
<titleInfo>
<title>Enhancing Descriptive Image Captioning with Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhan</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</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 2: Short 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>Generating descriptive sentences that convey non-trivial, detailed, and salient information about images is an important goal of image captioning. In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions. Specifically, we construct directed inference graphs for reference captions based on natural language inference. A PageRank algorithm is then employed to estimate the descriptiveness score of each node. Built on that, we use reference sampling and weighted designated rewards to guide captioning to generate descriptive captions. The results on MSCOCO show that the proposed method outperforms the baselines significantly on a wide range of conventional and descriptiveness-related evaluation metrics.</abstract>
<identifier type="citekey">shi-etal-2021-enhancing</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.36</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.36/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>269</start>
<end>277</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Descriptive Image Captioning with Natural Language Inference
%A Shi, Zhan
%A Liu, Hui
%A Zhu, Xiaodan
%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 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F shi-etal-2021-enhancing
%X Generating descriptive sentences that convey non-trivial, detailed, and salient information about images is an important goal of image captioning. In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions. Specifically, we construct directed inference graphs for reference captions based on natural language inference. A PageRank algorithm is then employed to estimate the descriptiveness score of each node. Built on that, we use reference sampling and weighted designated rewards to guide captioning to generate descriptive captions. The results on MSCOCO show that the proposed method outperforms the baselines significantly on a wide range of conventional and descriptiveness-related evaluation metrics.
%R 10.18653/v1/2021.acl-short.36
%U https://aclanthology.org/2021.acl-short.36/
%U https://doi.org/10.18653/v1/2021.acl-short.36
%P 269-277
Markdown (Informal)
[Enhancing Descriptive Image Captioning with Natural Language Inference](https://aclanthology.org/2021.acl-short.36/) (Shi et al., ACL-IJCNLP 2021)
ACL
- Zhan Shi, Hui Liu, and Xiaodan Zhu. 2021. Enhancing Descriptive Image Captioning with Natural Language Inference. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 269–277, Online. Association for Computational Linguistics.