@inproceedings{koper-schulte-im-walde-2017-complex,
title = "Complex Verbs are Different: Exploring the Visual Modality in Multi-Modal Models to Predict Compositionality",
author = {K{\"o}per, Maximilian and
Schulte im Walde, Sabine},
editor = "Markantonatou, Stella and
Ramisch, Carlos and
Savary, Agata and
Vincze, Veronika",
booktitle = "Proceedings of the 13th Workshop on Multiword Expressions ({MWE} 2017)",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1728",
doi = "10.18653/v1/W17-1728",
pages = "200--206",
abstract = "This paper compares a neural network DSM relying on textual co-occurrences with a multi-modal model integrating visual information. We focus on nominal vs. verbal compounds, and zoom into lexical, empirical and perceptual target properties to explore the contribution of the visual modality. Our experiments show that (i) visual features contribute differently for verbs than for nouns, and (ii) images complement textual information, if (a) the textual modality by itself is poor and appropriate image subsets are used, or (b) the textual modality by itself is rich and large (potentially noisy) images are added.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koper-schulte-im-walde-2017-complex">
<titleInfo>
<title>Complex Verbs are Different: Exploring the Visual Modality in Multi-Modal Models to Predict Compositionality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Köper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Schulte im Walde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Vincze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper compares a neural network DSM relying on textual co-occurrences with a multi-modal model integrating visual information. We focus on nominal vs. verbal compounds, and zoom into lexical, empirical and perceptual target properties to explore the contribution of the visual modality. Our experiments show that (i) visual features contribute differently for verbs than for nouns, and (ii) images complement textual information, if (a) the textual modality by itself is poor and appropriate image subsets are used, or (b) the textual modality by itself is rich and large (potentially noisy) images are added.</abstract>
<identifier type="citekey">koper-schulte-im-walde-2017-complex</identifier>
<identifier type="doi">10.18653/v1/W17-1728</identifier>
<location>
<url>https://aclanthology.org/W17-1728</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>200</start>
<end>206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Complex Verbs are Different: Exploring the Visual Modality in Multi-Modal Models to Predict Compositionality
%A Köper, Maximilian
%A Schulte im Walde, Sabine
%Y Markantonatou, Stella
%Y Ramisch, Carlos
%Y Savary, Agata
%Y Vincze, Veronika
%S Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F koper-schulte-im-walde-2017-complex
%X This paper compares a neural network DSM relying on textual co-occurrences with a multi-modal model integrating visual information. We focus on nominal vs. verbal compounds, and zoom into lexical, empirical and perceptual target properties to explore the contribution of the visual modality. Our experiments show that (i) visual features contribute differently for verbs than for nouns, and (ii) images complement textual information, if (a) the textual modality by itself is poor and appropriate image subsets are used, or (b) the textual modality by itself is rich and large (potentially noisy) images are added.
%R 10.18653/v1/W17-1728
%U https://aclanthology.org/W17-1728
%U https://doi.org/10.18653/v1/W17-1728
%P 200-206
Markdown (Informal)
[Complex Verbs are Different: Exploring the Visual Modality in Multi-Modal Models to Predict Compositionality](https://aclanthology.org/W17-1728) (Köper & Schulte im Walde, MWE 2017)
ACL