@inproceedings{platonov-etal-2021-modeling,
title = "Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives",
author = "Platonov, Georgiy and
Yang, Yifei and
Wu, Haoyu and
Waxman, Jonathan and
Hill, Marcus and
Schubert, Lenhart",
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-1.4",
doi = "10.18653/v1/2021.splurobonlp-1.4",
pages = "32--41",
abstract = "Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction. However, capturing the semantics and appropriate usage of spatial prepositions is notoriously difficult, because of their vagueness and polysemy. Although modern data-driven approaches are good at capturing statistical regularities in the usage, they usually require substantial sample sizes, often do not generalize well to unseen instances and, most importantly, their structure is essentially opaque to analysis, which makes diagnosing problems and understanding their reasoning process difficult. In this work, we discuss our attempt at modeling spatial senses of prepositions in English using a combination of rule-based and statistical learning approaches. Each preposition model is implemented as a tree where each node computes certain intuitive relations associated with the preposition, with the root computing the final value of the prepositional relation itself. The models operate on a set of artificial 3D {``}room world{''} environments, designed in Blender, taking the scene itself as an input. We also discuss our annotation framework used to collect human judgments employed in the model training. Both our factored models and black-box baseline models perform quite well, but the factored models will enable reasoned explanations of spatial relation judgements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="platonov-etal-2021-modeling">
<titleInfo>
<title>Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georgiy</namePart>
<namePart type="family">Platonov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Waxman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Hill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lenhart</namePart>
<namePart type="family">Schubert</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>Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction. However, capturing the semantics and appropriate usage of spatial prepositions is notoriously difficult, because of their vagueness and polysemy. Although modern data-driven approaches are good at capturing statistical regularities in the usage, they usually require substantial sample sizes, often do not generalize well to unseen instances and, most importantly, their structure is essentially opaque to analysis, which makes diagnosing problems and understanding their reasoning process difficult. In this work, we discuss our attempt at modeling spatial senses of prepositions in English using a combination of rule-based and statistical learning approaches. Each preposition model is implemented as a tree where each node computes certain intuitive relations associated with the preposition, with the root computing the final value of the prepositional relation itself. The models operate on a set of artificial 3D “room world” environments, designed in Blender, taking the scene itself as an input. We also discuss our annotation framework used to collect human judgments employed in the model training. Both our factored models and black-box baseline models perform quite well, but the factored models will enable reasoned explanations of spatial relation judgements.</abstract>
<identifier type="citekey">platonov-etal-2021-modeling</identifier>
<identifier type="doi">10.18653/v1/2021.splurobonlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2021.splurobonlp-1.4</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>32</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives
%A Platonov, Georgiy
%A Yang, Yifei
%A Wu, Haoyu
%A Waxman, Jonathan
%A Hill, Marcus
%A Schubert, Lenhart
%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 platonov-etal-2021-modeling
%X Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction. However, capturing the semantics and appropriate usage of spatial prepositions is notoriously difficult, because of their vagueness and polysemy. Although modern data-driven approaches are good at capturing statistical regularities in the usage, they usually require substantial sample sizes, often do not generalize well to unseen instances and, most importantly, their structure is essentially opaque to analysis, which makes diagnosing problems and understanding their reasoning process difficult. In this work, we discuss our attempt at modeling spatial senses of prepositions in English using a combination of rule-based and statistical learning approaches. Each preposition model is implemented as a tree where each node computes certain intuitive relations associated with the preposition, with the root computing the final value of the prepositional relation itself. The models operate on a set of artificial 3D “room world” environments, designed in Blender, taking the scene itself as an input. We also discuss our annotation framework used to collect human judgments employed in the model training. Both our factored models and black-box baseline models perform quite well, but the factored models will enable reasoned explanations of spatial relation judgements.
%R 10.18653/v1/2021.splurobonlp-1.4
%U https://aclanthology.org/2021.splurobonlp-1.4
%U https://doi.org/10.18653/v1/2021.splurobonlp-1.4
%P 32-41
Markdown (Informal)
[Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives](https://aclanthology.org/2021.splurobonlp-1.4) (Platonov et al., splurobonlp 2021)
ACL