@inproceedings{liu-etal-2024-look,
title = "Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation",
author = "Liu, Xumeng and
Guo, Wenya and
Zhang, Ying and
Liu, Xubo and
Zhao, Yu and
Yu, Shenglong and
Yuan, Xiaojie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.943",
pages = "10802--10812",
abstract = "Knowledge-based Visual Question Generation aims to generate visual questions with outside knowledge other than the image. Existing approaches are answer-aware, which incorporate answers into the question-generation process. However, these methods just focus on leveraging the semantics of inputs to propose questions, ignoring the logical coherence among generated questions (Q), images (V), answers (A), and corresponding acquired outside knowledge (K). It results in generating many non-expected questions with low quality, lacking insight and diversity, and some of them are even without any corresponding answer. To address this issue, we inject logical verification into the processes of knowledge acquisition and question generation, which is defined as LV{\^{}}2-Net. Through checking the logical structure among V, A, K, ground-truth and generated Q twice in the whole KB-VQG procedure, LV{\^{}}2-Net can propose diverse and insightful knowledge-based visual questions. And experimental results on two commonly used datasets demonstrate the superiority of LV{\^{}}2-Net. Our code will be released to the public soon.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-look">
<titleInfo>
<title>Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xumeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenya</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xubo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shenglong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Yuan</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>Knowledge-based Visual Question Generation aims to generate visual questions with outside knowledge other than the image. Existing approaches are answer-aware, which incorporate answers into the question-generation process. However, these methods just focus on leveraging the semantics of inputs to propose questions, ignoring the logical coherence among generated questions (Q), images (V), answers (A), and corresponding acquired outside knowledge (K). It results in generating many non-expected questions with low quality, lacking insight and diversity, and some of them are even without any corresponding answer. To address this issue, we inject logical verification into the processes of knowledge acquisition and question generation, which is defined as LV\²-Net. Through checking the logical structure among V, A, K, ground-truth and generated Q twice in the whole KB-VQG procedure, LV\²-Net can propose diverse and insightful knowledge-based visual questions. And experimental results on two commonly used datasets demonstrate the superiority of LV\²-Net. Our code will be released to the public soon.</abstract>
<identifier type="citekey">liu-etal-2024-look</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.943</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10802</start>
<end>10812</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation
%A Liu, Xumeng
%A Guo, Wenya
%A Zhang, Ying
%A Liu, Xubo
%A Zhao, Yu
%A Yu, Shenglong
%A Yuan, Xiaojie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F liu-etal-2024-look
%X Knowledge-based Visual Question Generation aims to generate visual questions with outside knowledge other than the image. Existing approaches are answer-aware, which incorporate answers into the question-generation process. However, these methods just focus on leveraging the semantics of inputs to propose questions, ignoring the logical coherence among generated questions (Q), images (V), answers (A), and corresponding acquired outside knowledge (K). It results in generating many non-expected questions with low quality, lacking insight and diversity, and some of them are even without any corresponding answer. To address this issue, we inject logical verification into the processes of knowledge acquisition and question generation, which is defined as LV\²-Net. Through checking the logical structure among V, A, K, ground-truth and generated Q twice in the whole KB-VQG procedure, LV\²-Net can propose diverse and insightful knowledge-based visual questions. And experimental results on two commonly used datasets demonstrate the superiority of LV\²-Net. Our code will be released to the public soon.
%U https://aclanthology.org/2024.lrec-main.943
%P 10802-10812
Markdown (Informal)
[Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation](https://aclanthology.org/2024.lrec-main.943) (Liu et al., LREC-COLING 2024)
ACL
- Xumeng Liu, Wenya Guo, Ying Zhang, Xubo Liu, Yu Zhao, Shenglong Yu, and Xiaojie Yuan. 2024. Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10802–10812, Torino, Italia. ELRA and ICCL.