@inproceedings{ebert-pavlick-2020-visuospatial,
title = "A Visuospatial Dataset for Naturalistic Verb Learning",
author = "Ebert, Dylan and
Pavlick, Ellie",
editor = "Gurevych, Iryna and
Apidianaki, Marianna and
Faruqui, Manaal",
booktitle = "Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.starsem-1.16/",
pages = "143--153",
abstract = "We introduce a new dataset for training and evaluating grounded language models. Our data is collected within a virtual reality environment and is designed to emulate the quality of language data to which a pre-verbal child is likely to have access: That is, naturalistic, spontaneous speech paired with richly grounded visuospatial context. We use the collected data to compare several distributional semantics models for verb learning. We evaluate neural models based on 2D (pixel) features as well as feature-engineered models based on 3D (symbolic, spatial) features, and show that neither modeling approach achieves satisfactory performance. Our results are consistent with evidence from child language acquisition that emphasizes the difficulty of learning verbs from naive distributional data. We discuss avenues for future work on cognitively-inspired grounded language learning, and release our corpus with the intent of facilitating research on the topic."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ebert-pavlick-2020-visuospatial">
<titleInfo>
<title>A Visuospatial Dataset for Naturalistic Verb Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dylan</namePart>
<namePart type="family">Ebert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Pavlick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manaal</namePart>
<namePart type="family">Faruqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a new dataset for training and evaluating grounded language models. Our data is collected within a virtual reality environment and is designed to emulate the quality of language data to which a pre-verbal child is likely to have access: That is, naturalistic, spontaneous speech paired with richly grounded visuospatial context. We use the collected data to compare several distributional semantics models for verb learning. We evaluate neural models based on 2D (pixel) features as well as feature-engineered models based on 3D (symbolic, spatial) features, and show that neither modeling approach achieves satisfactory performance. Our results are consistent with evidence from child language acquisition that emphasizes the difficulty of learning verbs from naive distributional data. We discuss avenues for future work on cognitively-inspired grounded language learning, and release our corpus with the intent of facilitating research on the topic.</abstract>
<identifier type="citekey">ebert-pavlick-2020-visuospatial</identifier>
<location>
<url>https://aclanthology.org/2020.starsem-1.16/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>143</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Visuospatial Dataset for Naturalistic Verb Learning
%A Ebert, Dylan
%A Pavlick, Ellie
%Y Gurevych, Iryna
%Y Apidianaki, Marianna
%Y Faruqui, Manaal
%S Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F ebert-pavlick-2020-visuospatial
%X We introduce a new dataset for training and evaluating grounded language models. Our data is collected within a virtual reality environment and is designed to emulate the quality of language data to which a pre-verbal child is likely to have access: That is, naturalistic, spontaneous speech paired with richly grounded visuospatial context. We use the collected data to compare several distributional semantics models for verb learning. We evaluate neural models based on 2D (pixel) features as well as feature-engineered models based on 3D (symbolic, spatial) features, and show that neither modeling approach achieves satisfactory performance. Our results are consistent with evidence from child language acquisition that emphasizes the difficulty of learning verbs from naive distributional data. We discuss avenues for future work on cognitively-inspired grounded language learning, and release our corpus with the intent of facilitating research on the topic.
%U https://aclanthology.org/2020.starsem-1.16/
%P 143-153
Markdown (Informal)
[A Visuospatial Dataset for Naturalistic Verb Learning](https://aclanthology.org/2020.starsem-1.16/) (Ebert & Pavlick, *SEM 2020)
ACL