@inproceedings{merullo-etal-2022-pretraining,
title = "Pretraining on Interactions for Learning Grounded Affordance Representations",
author = "Merullo, Jack and
Ebert, Dylan and
Eickhoff, Carsten and
Pavlick, Ellie",
editor = "Nastase, Vivi and
Pavlick, Ellie and
Pilehvar, Mohammad Taher and
Camacho-Collados, Jose and
Raganato, Alessandro",
booktitle = "Proceedings of the 11th Joint Conference on Lexical and Computational Semantics",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.starsem-1.23",
doi = "10.18653/v1/2022.starsem-1.23",
pages = "258--277",
abstract = "Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with the ?foundation? models that currently dominate language representation research. We hypothesize that predictive modeling of object state over time will result in representations that encode object affordance information ?for free?. We train a neural network to predict objects? trajectories in a simulated interaction and show that our network?s latent representations differentiate between both observed and unobserved affordances. We find that models trained using 3D simulations outperform conventional 2D computer vision models trained on a similar task, and, on initial inspection, that differences between concepts correspond to expected features (e.g., roll entails rotation) . Our results suggest a way in which modern deep learning approaches to grounded language learning can be integrated with traditional formal semantic notions of lexical representations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="merullo-etal-2022-pretraining">
<titleInfo>
<title>Pretraining on Interactions for Learning Grounded Affordance Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Merullo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Carsten</namePart>
<namePart type="family">Eickhoff</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>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Joint Conference on Lexical and Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivi</namePart>
<namePart type="family">Nastase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Pavlick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Raganato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with the ?foundation? models that currently dominate language representation research. We hypothesize that predictive modeling of object state over time will result in representations that encode object affordance information ?for free?. We train a neural network to predict objects? trajectories in a simulated interaction and show that our network?s latent representations differentiate between both observed and unobserved affordances. We find that models trained using 3D simulations outperform conventional 2D computer vision models trained on a similar task, and, on initial inspection, that differences between concepts correspond to expected features (e.g., roll entails rotation) . Our results suggest a way in which modern deep learning approaches to grounded language learning can be integrated with traditional formal semantic notions of lexical representations.</abstract>
<identifier type="citekey">merullo-etal-2022-pretraining</identifier>
<identifier type="doi">10.18653/v1/2022.starsem-1.23</identifier>
<location>
<url>https://aclanthology.org/2022.starsem-1.23</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>258</start>
<end>277</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pretraining on Interactions for Learning Grounded Affordance Representations
%A Merullo, Jack
%A Ebert, Dylan
%A Eickhoff, Carsten
%A Pavlick, Ellie
%Y Nastase, Vivi
%Y Pavlick, Ellie
%Y Pilehvar, Mohammad Taher
%Y Camacho-Collados, Jose
%Y Raganato, Alessandro
%S Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F merullo-etal-2022-pretraining
%X Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with the ?foundation? models that currently dominate language representation research. We hypothesize that predictive modeling of object state over time will result in representations that encode object affordance information ?for free?. We train a neural network to predict objects? trajectories in a simulated interaction and show that our network?s latent representations differentiate between both observed and unobserved affordances. We find that models trained using 3D simulations outperform conventional 2D computer vision models trained on a similar task, and, on initial inspection, that differences between concepts correspond to expected features (e.g., roll entails rotation) . Our results suggest a way in which modern deep learning approaches to grounded language learning can be integrated with traditional formal semantic notions of lexical representations.
%R 10.18653/v1/2022.starsem-1.23
%U https://aclanthology.org/2022.starsem-1.23
%U https://doi.org/10.18653/v1/2022.starsem-1.23
%P 258-277
Markdown (Informal)
[Pretraining on Interactions for Learning Grounded Affordance Representations](https://aclanthology.org/2022.starsem-1.23) (Merullo et al., *SEM 2022)
ACL