@inproceedings{liu-etal-2024-knowledge,
title = "Knowledge-Guided Cross-Topic Visual Question Generation",
author = "Liu, Hongfei and
Wang, Guohua and
Xie, Jiayuan and
Chen, Jiali and
Fang, Wenhao and
Cai, Yi",
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.861/",
pages = "9854--9864",
abstract = "Visual question generation (VQG) task aims to generate high-quality questions based on the input image. Current methods primarily focus on generating questions containing specified content utilizing answers or question types as constraints. However, these constraints make it challenging to control the topic of generated questions (e.g., conversation or test subject topics) for various applications. Thus, it is necessary to utilize topics as constraints to guide question generation. Considering that there are many topics and it is almost impossible for human annotations to cover them, we propose the cross-topic learning VQG (CTL-VQG) task, which aims to generate questions related to unseen topics in cross-topic scenarios. In this paper, we propose a knowledge-guided cross-topic visual question generation (KC-VQG) model to extract unseen topic-related information for question generation. Specifically, an image-topic feature extractor is introduced in our model to extract topic-related intuitive visual features; an image-topic knowledge extractor is used to extract and select the most appropriate topic-related implicit knowledge from large language models for generating questions. Extensive experiments show that our model outperforms baselines and can effectively generate unseen topic-related questions in cross-topic scenarios."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-knowledge">
<titleInfo>
<title>Knowledge-Guided Cross-Topic Visual Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guohua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayuan</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiali</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Cai</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>Visual question generation (VQG) task aims to generate high-quality questions based on the input image. Current methods primarily focus on generating questions containing specified content utilizing answers or question types as constraints. However, these constraints make it challenging to control the topic of generated questions (e.g., conversation or test subject topics) for various applications. Thus, it is necessary to utilize topics as constraints to guide question generation. Considering that there are many topics and it is almost impossible for human annotations to cover them, we propose the cross-topic learning VQG (CTL-VQG) task, which aims to generate questions related to unseen topics in cross-topic scenarios. In this paper, we propose a knowledge-guided cross-topic visual question generation (KC-VQG) model to extract unseen topic-related information for question generation. Specifically, an image-topic feature extractor is introduced in our model to extract topic-related intuitive visual features; an image-topic knowledge extractor is used to extract and select the most appropriate topic-related implicit knowledge from large language models for generating questions. Extensive experiments show that our model outperforms baselines and can effectively generate unseen topic-related questions in cross-topic scenarios.</abstract>
<identifier type="citekey">liu-etal-2024-knowledge</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.861/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9854</start>
<end>9864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge-Guided Cross-Topic Visual Question Generation
%A Liu, Hongfei
%A Wang, Guohua
%A Xie, Jiayuan
%A Chen, Jiali
%A Fang, Wenhao
%A Cai, Yi
%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-knowledge
%X Visual question generation (VQG) task aims to generate high-quality questions based on the input image. Current methods primarily focus on generating questions containing specified content utilizing answers or question types as constraints. However, these constraints make it challenging to control the topic of generated questions (e.g., conversation or test subject topics) for various applications. Thus, it is necessary to utilize topics as constraints to guide question generation. Considering that there are many topics and it is almost impossible for human annotations to cover them, we propose the cross-topic learning VQG (CTL-VQG) task, which aims to generate questions related to unseen topics in cross-topic scenarios. In this paper, we propose a knowledge-guided cross-topic visual question generation (KC-VQG) model to extract unseen topic-related information for question generation. Specifically, an image-topic feature extractor is introduced in our model to extract topic-related intuitive visual features; an image-topic knowledge extractor is used to extract and select the most appropriate topic-related implicit knowledge from large language models for generating questions. Extensive experiments show that our model outperforms baselines and can effectively generate unseen topic-related questions in cross-topic scenarios.
%U https://aclanthology.org/2024.lrec-main.861/
%P 9854-9864
Markdown (Informal)
[Knowledge-Guided Cross-Topic Visual Question Generation](https://aclanthology.org/2024.lrec-main.861/) (Liu et al., LREC-COLING 2024)
ACL
- Hongfei Liu, Guohua Wang, Jiayuan Xie, Jiali Chen, Wenhao Fang, and Yi Cai. 2024. Knowledge-Guided Cross-Topic Visual Question Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9854–9864, Torino, Italia. ELRA and ICCL.