@inproceedings{dong-etal-2021-visually,
title = "Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History",
author = "Dong, Tianai and
Testoni, Alberto and
Benotti, Luciana and
Bernardi, Raffaella",
editor = "Alikhani, Malihe and
Blukis, Valts and
Kordjamshidi, Parisa and
Padmakumar, Aishwarya and
Tan, Hao",
booktitle = "Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.splurobonlp-1.3",
doi = "10.18653/v1/2021.splurobonlp-1.3",
pages = "22--31",
abstract = "In this paper, we define and evaluate a methodology for extracting history-dependent spatial questions from visual dialogues. We say that a question is history-dependent if it requires (parts of) its dialogue history to be interpreted. We argue that some kinds of visual questions define a context upon which a follow-up spatial question relies. We call the question that restricts the context: trigger, and we call the spatial question that requires the trigger question to be answered: zoomer. We automatically extract different trigger and zoomer pairs based on the visual property that the questions rely on (e.g. color, number). We manually annotate the automatically extracted trigger and zoomer pairs to verify which zoomers require their trigger. We implement a simple baseline architecture based on a SOTA multimodal encoder. Our results reveal that there is much room for improvement for answering history-dependent questions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2021-visually">
<titleInfo>
<title>Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianai</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Testoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</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 Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valts</namePart>
<namePart type="family">Blukis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parisa</namePart>
<namePart type="family">Kordjamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Tan</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>In this paper, we define and evaluate a methodology for extracting history-dependent spatial questions from visual dialogues. We say that a question is history-dependent if it requires (parts of) its dialogue history to be interpreted. We argue that some kinds of visual questions define a context upon which a follow-up spatial question relies. We call the question that restricts the context: trigger, and we call the spatial question that requires the trigger question to be answered: zoomer. We automatically extract different trigger and zoomer pairs based on the visual property that the questions rely on (e.g. color, number). We manually annotate the automatically extracted trigger and zoomer pairs to verify which zoomers require their trigger. We implement a simple baseline architecture based on a SOTA multimodal encoder. Our results reveal that there is much room for improvement for answering history-dependent questions.</abstract>
<identifier type="citekey">dong-etal-2021-visually</identifier>
<identifier type="doi">10.18653/v1/2021.splurobonlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.splurobonlp-1.3</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>22</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History
%A Dong, Tianai
%A Testoni, Alberto
%A Benotti, Luciana
%A Bernardi, Raffaella
%Y Alikhani, Malihe
%Y Blukis, Valts
%Y Kordjamshidi, Parisa
%Y Padmakumar, Aishwarya
%Y Tan, Hao
%S Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F dong-etal-2021-visually
%X In this paper, we define and evaluate a methodology for extracting history-dependent spatial questions from visual dialogues. We say that a question is history-dependent if it requires (parts of) its dialogue history to be interpreted. We argue that some kinds of visual questions define a context upon which a follow-up spatial question relies. We call the question that restricts the context: trigger, and we call the spatial question that requires the trigger question to be answered: zoomer. We automatically extract different trigger and zoomer pairs based on the visual property that the questions rely on (e.g. color, number). We manually annotate the automatically extracted trigger and zoomer pairs to verify which zoomers require their trigger. We implement a simple baseline architecture based on a SOTA multimodal encoder. Our results reveal that there is much room for improvement for answering history-dependent questions.
%R 10.18653/v1/2021.splurobonlp-1.3
%U https://aclanthology.org/2021.splurobonlp-1.3
%U https://doi.org/10.18653/v1/2021.splurobonlp-1.3
%P 22-31
Markdown (Informal)
[Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History](https://aclanthology.org/2021.splurobonlp-1.3) (Dong et al., splurobonlp 2021)
ACL