@inproceedings{nazir-sadrzadeh-2024-adjective,
title = "How Does an Adjective Sound Like? Exploring Audio Phrase Composition with Textual Embeddings",
author = "Nazir, Saba and
Sadrzadeh, Mehrnoosh",
editor = "Qiu, Amy and
Noble, Bill and
Pagmar, David and
Maraev, Vladislav and
Ilinykh, Nikolai",
booktitle = "Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning",
month = oct,
year = "2024",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clasp-1.3",
pages = "13--18",
abstract = "We learn matrix representations for the fre- quent sound-relevant adjectives of English and compose them with vector representations of their nouns. The matrices are learnt jointly from audio and textual data, via linear regres- sion and tensor skipgram. They are assessed using an adjective similarity benchmark and also a novel adjective-noun phrase similarity dataset, applied to two tasks: semantic similar- ity and audio similarity. Joint learning via Ten- sor Skipgram (TSG) outperforms audio-only models, matrix composition outperforms addi- tion and non compositional phrase vectors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nazir-sadrzadeh-2024-adjective">
<titleInfo>
<title>How Does an Adjective Sound Like? Exploring Audio Phrase Composition with Textual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saba</namePart>
<namePart type="family">Nazir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrnoosh</namePart>
<namePart type="family">Sadrzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="family">Noble</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Pagmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Maraev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We learn matrix representations for the fre- quent sound-relevant adjectives of English and compose them with vector representations of their nouns. The matrices are learnt jointly from audio and textual data, via linear regres- sion and tensor skipgram. They are assessed using an adjective similarity benchmark and also a novel adjective-noun phrase similarity dataset, applied to two tasks: semantic similar- ity and audio similarity. Joint learning via Ten- sor Skipgram (TSG) outperforms audio-only models, matrix composition outperforms addi- tion and non compositional phrase vectors.</abstract>
<identifier type="citekey">nazir-sadrzadeh-2024-adjective</identifier>
<location>
<url>https://aclanthology.org/2024.clasp-1.3</url>
</location>
<part>
<date>2024-10</date>
<extent unit="page">
<start>13</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Does an Adjective Sound Like? Exploring Audio Phrase Composition with Textual Embeddings
%A Nazir, Saba
%A Sadrzadeh, Mehrnoosh
%Y Qiu, Amy
%Y Noble, Bill
%Y Pagmar, David
%Y Maraev, Vladislav
%Y Ilinykh, Nikolai
%S Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning
%D 2024
%8 October
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F nazir-sadrzadeh-2024-adjective
%X We learn matrix representations for the fre- quent sound-relevant adjectives of English and compose them with vector representations of their nouns. The matrices are learnt jointly from audio and textual data, via linear regres- sion and tensor skipgram. They are assessed using an adjective similarity benchmark and also a novel adjective-noun phrase similarity dataset, applied to two tasks: semantic similar- ity and audio similarity. Joint learning via Ten- sor Skipgram (TSG) outperforms audio-only models, matrix composition outperforms addi- tion and non compositional phrase vectors.
%U https://aclanthology.org/2024.clasp-1.3
%P 13-18
Markdown (Informal)
[How Does an Adjective Sound Like? Exploring Audio Phrase Composition with Textual Embeddings](https://aclanthology.org/2024.clasp-1.3) (Nazir & Sadrzadeh, CLASP 2024)
ACL