@inproceedings{pezzelle-fernandez-2019-big,
title = "Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size",
author = "Pezzelle, Sandro and
Fern{\'a}ndez, Raquel",
editor = "Mogadala, Aditya and
Klakow, Dietrich and
Pezzelle, Sandro and
Moens, Marie-Francine",
booktitle = "Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6403",
doi = "10.18653/v1/D19-6403",
pages = "18--23",
abstract = "In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities {--} modeling the multimodal, contextually-dependent meaning of size adjectives ({`}big{'}, {`}small{'}) {--} and explore the impact of varying the training data on the learning behavior of a state-of-art system. In previous work, models have been shown to fail in generalizing to unseen adjective-noun combinations. Here, we investigate whether, and to what extent, seeing some of these cases during training helps a model understand the rule subtending the task, i.e., that being big implies being not small, and vice versa. We show that relatively few examples are enough to understand this relationship, and that developing a specific, mutually exclusive representation of size adjectives is beneficial to the task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pezzelle-fernandez-2019-big">
<titleInfo>
<title>Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Mogadala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandro</namePart>
<namePart type="family">Pezzelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities – modeling the multimodal, contextually-dependent meaning of size adjectives (‘big’, ‘small’) – and explore the impact of varying the training data on the learning behavior of a state-of-art system. In previous work, models have been shown to fail in generalizing to unseen adjective-noun combinations. Here, we investigate whether, and to what extent, seeing some of these cases during training helps a model understand the rule subtending the task, i.e., that being big implies being not small, and vice versa. We show that relatively few examples are enough to understand this relationship, and that developing a specific, mutually exclusive representation of size adjectives is beneficial to the task.</abstract>
<identifier type="citekey">pezzelle-fernandez-2019-big</identifier>
<identifier type="doi">10.18653/v1/D19-6403</identifier>
<location>
<url>https://aclanthology.org/D19-6403</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>18</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size
%A Pezzelle, Sandro
%A Fernández, Raquel
%Y Mogadala, Aditya
%Y Klakow, Dietrich
%Y Pezzelle, Sandro
%Y Moens, Marie-Francine
%S Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F pezzelle-fernandez-2019-big
%X In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities – modeling the multimodal, contextually-dependent meaning of size adjectives (‘big’, ‘small’) – and explore the impact of varying the training data on the learning behavior of a state-of-art system. In previous work, models have been shown to fail in generalizing to unseen adjective-noun combinations. Here, we investigate whether, and to what extent, seeing some of these cases during training helps a model understand the rule subtending the task, i.e., that being big implies being not small, and vice versa. We show that relatively few examples are enough to understand this relationship, and that developing a specific, mutually exclusive representation of size adjectives is beneficial to the task.
%R 10.18653/v1/D19-6403
%U https://aclanthology.org/D19-6403
%U https://doi.org/10.18653/v1/D19-6403
%P 18-23
Markdown (Informal)
[Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size](https://aclanthology.org/D19-6403) (Pezzelle & Fernández, 2019)
ACL