@inproceedings{vedd-etal-2022-guiding,
title = "Guiding Visual Question Generation",
author = "Vedd, Nihir and
Wang, Zixu and
Rei, Marek and
Miao, Yishu and
Specia, Lucia",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.118",
doi = "10.18653/v1/2022.naacl-main.118",
pages = "1640--1654",
abstract = "In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their training data. This makes training difficult and also poses issues for evaluation {--} multiple valid questions exist for most images but only one or a few are captured by the human references. We present Guiding Visual Question Generation - a variant of VQG which conditions the question generator on categorical information based on expectations on the type of question and the objects it should explore. We propose two variant families: (i) an explicitly guided model that enables an actor (human or automated) to select which objects and categories to generate a question for; and (ii) 2 types of implicitly guided models that learn which objects and categories to condition on, based on discrete variables. The proposed models are evaluated on an answer-category augmented VQA dataset and our quantitative results show a substantial improvement over the current state of the art (over 9 BLEU-4 increase). Human evaluation validates that guidance helps the generation of questions that are grammatically coherent and relevant to the given image and objects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vedd-etal-2022-guiding">
<titleInfo>
<title>Guiding Visual Question Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nihir</namePart>
<namePart type="family">Vedd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yishu</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their training data. This makes training difficult and also poses issues for evaluation – multiple valid questions exist for most images but only one or a few are captured by the human references. We present Guiding Visual Question Generation - a variant of VQG which conditions the question generator on categorical information based on expectations on the type of question and the objects it should explore. We propose two variant families: (i) an explicitly guided model that enables an actor (human or automated) to select which objects and categories to generate a question for; and (ii) 2 types of implicitly guided models that learn which objects and categories to condition on, based on discrete variables. The proposed models are evaluated on an answer-category augmented VQA dataset and our quantitative results show a substantial improvement over the current state of the art (over 9 BLEU-4 increase). Human evaluation validates that guidance helps the generation of questions that are grammatically coherent and relevant to the given image and objects.</abstract>
<identifier type="citekey">vedd-etal-2022-guiding</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.118</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.118</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1640</start>
<end>1654</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Guiding Visual Question Generation
%A Vedd, Nihir
%A Wang, Zixu
%A Rei, Marek
%A Miao, Yishu
%A Specia, Lucia
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F vedd-etal-2022-guiding
%X In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their training data. This makes training difficult and also poses issues for evaluation – multiple valid questions exist for most images but only one or a few are captured by the human references. We present Guiding Visual Question Generation - a variant of VQG which conditions the question generator on categorical information based on expectations on the type of question and the objects it should explore. We propose two variant families: (i) an explicitly guided model that enables an actor (human or automated) to select which objects and categories to generate a question for; and (ii) 2 types of implicitly guided models that learn which objects and categories to condition on, based on discrete variables. The proposed models are evaluated on an answer-category augmented VQA dataset and our quantitative results show a substantial improvement over the current state of the art (over 9 BLEU-4 increase). Human evaluation validates that guidance helps the generation of questions that are grammatically coherent and relevant to the given image and objects.
%R 10.18653/v1/2022.naacl-main.118
%U https://aclanthology.org/2022.naacl-main.118
%U https://doi.org/10.18653/v1/2022.naacl-main.118
%P 1640-1654
Markdown (Informal)
[Guiding Visual Question Generation](https://aclanthology.org/2022.naacl-main.118) (Vedd et al., NAACL 2022)
ACL
- Nihir Vedd, Zixu Wang, Marek Rei, Yishu Miao, and Lucia Specia. 2022. Guiding Visual Question Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1640–1654, Seattle, United States. Association for Computational Linguistics.