@inproceedings{muraoka-etal-2020-visual,
title = "Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment",
author = "Muraoka, Masayasu and
Nasukawa, Tetsuya and
Bhattacharjee, Bishwaranjan",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.246",
doi = "10.18653/v1/2020.findings-emnlp.246",
pages = "2723--2735",
abstract = "We propose a new word representation method derived from visual objects in associated images to tackle the lexical entailment task. Although it has been shown that the \textit{Distributional Informativeness Hypothesis} (DIH) holds on text, in which the DIH assumes that a context surrounding a hyponym is more informative than that of a hypernym, it has never been tested on visual objects. Since our perception is tightly associated with language, it is meaningful to explore whether the DIH holds on visual objects. To this end, we consider visual objects as the context of a word and represent a word as a bag of visual objects found in images associated with the word. This allows us to test the feasibility of the visual DIH. To better distinguish word pairs in a hypernym relation from other relations such as co-hypernyms, we also propose a new measurable function that takes into account both the difference in the generality of meaning and similarity of meaning between words. Our experimental results show that the DIH holds on visual objects and that the proposed method combined with the proposed function outperforms existing unsupervised representation methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muraoka-etal-2020-visual">
<titleInfo>
<title>Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masayasu</namePart>
<namePart type="family">Muraoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuya</namePart>
<namePart type="family">Nasukawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bishwaranjan</namePart>
<namePart type="family">Bhattacharjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>We propose a new word representation method derived from visual objects in associated images to tackle the lexical entailment task. Although it has been shown that the Distributional Informativeness Hypothesis (DIH) holds on text, in which the DIH assumes that a context surrounding a hyponym is more informative than that of a hypernym, it has never been tested on visual objects. Since our perception is tightly associated with language, it is meaningful to explore whether the DIH holds on visual objects. To this end, we consider visual objects as the context of a word and represent a word as a bag of visual objects found in images associated with the word. This allows us to test the feasibility of the visual DIH. To better distinguish word pairs in a hypernym relation from other relations such as co-hypernyms, we also propose a new measurable function that takes into account both the difference in the generality of meaning and similarity of meaning between words. Our experimental results show that the DIH holds on visual objects and that the proposed method combined with the proposed function outperforms existing unsupervised representation methods.</abstract>
<identifier type="citekey">muraoka-etal-2020-visual</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.246</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.246</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2723</start>
<end>2735</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment
%A Muraoka, Masayasu
%A Nasukawa, Tetsuya
%A Bhattacharjee, Bishwaranjan
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F muraoka-etal-2020-visual
%X We propose a new word representation method derived from visual objects in associated images to tackle the lexical entailment task. Although it has been shown that the Distributional Informativeness Hypothesis (DIH) holds on text, in which the DIH assumes that a context surrounding a hyponym is more informative than that of a hypernym, it has never been tested on visual objects. Since our perception is tightly associated with language, it is meaningful to explore whether the DIH holds on visual objects. To this end, we consider visual objects as the context of a word and represent a word as a bag of visual objects found in images associated with the word. This allows us to test the feasibility of the visual DIH. To better distinguish word pairs in a hypernym relation from other relations such as co-hypernyms, we also propose a new measurable function that takes into account both the difference in the generality of meaning and similarity of meaning between words. Our experimental results show that the DIH holds on visual objects and that the proposed method combined with the proposed function outperforms existing unsupervised representation methods.
%R 10.18653/v1/2020.findings-emnlp.246
%U https://aclanthology.org/2020.findings-emnlp.246
%U https://doi.org/10.18653/v1/2020.findings-emnlp.246
%P 2723-2735
Markdown (Informal)
[Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment](https://aclanthology.org/2020.findings-emnlp.246) (Muraoka et al., Findings 2020)
ACL