GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings

Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-10
Hauptverfasser: Ali, Muhammad Asif, Alshmrani, Maha, Qin, Jianbin, Hu, Yan, Wang, Di
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Ali, Muhammad Asif
Alshmrani, Maha
Qin, Jianbin
Hu, Yan
Wang, Di
description Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model training objective. To address this, we propose GARI that combines the distributional training objectives with multiple isomorphism losses guided by the graph attention network. GARI considers the impact of semantical variations of words in order to define the relative isomorphism of the embedding spaces. Experimental evaluation using the Arabic language data set shows that GARI outperforms the existing research by improving the average P@1 by a relative score of up to 40.95% and 76.80% for in-domain and domain mismatch settings respectively. We release the codes for GARI at https://github.com/asif6827/GARI.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2880584850</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2880584850</sourcerecordid><originalsourceid>FETCH-proquest_journals_28805848503</originalsourceid><addsrcrecordid>eNqNykELgjAYgOERBEn5Hz7oLKzpanSTMPUqQUeZOXOi-2yb_f469AM6vYfnXZGAxfEhEgljGxI6N1BK2fHEOI8DUuRpVZ4ht3LuIfVeGa_RQIcWKjVKr98KSocT2rnXbgLsILWy0Q-4o20hmxrVtto83Y6sOzk6Ff66JftrdrsU0WzxtSjn6wEXa75UMyEoF4ngNP7v-gCvzzsU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2880584850</pqid></control><display><type>article</type><title>GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings</title><source>Free E- Journals</source><creator>Ali, Muhammad Asif ; Alshmrani, Maha ; Qin, Jianbin ; Hu, Yan ; Wang, Di</creator><creatorcontrib>Ali, Muhammad Asif ; Alshmrani, Maha ; Qin, Jianbin ; Hu, Yan ; Wang, Di</creatorcontrib><description>Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model training objective. To address this, we propose GARI that combines the distributional training objectives with multiple isomorphism losses guided by the graph attention network. GARI considers the impact of semantical variations of words in order to define the relative isomorphism of the embedding spaces. Experimental evaluation using the Arabic language data set shows that GARI outperforms the existing research by improving the average P@1 by a relative score of up to 40.95% and 76.80% for in-domain and domain mismatch settings respectively. We release the codes for GARI at https://github.com/asif6827/GARI.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Embedding ; Isomorphism ; Training ; Words (language)</subject><ispartof>arXiv.org, 2023-10</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>777,781</link.rule.ids></links><search><creatorcontrib>Ali, Muhammad Asif</creatorcontrib><creatorcontrib>Alshmrani, Maha</creatorcontrib><creatorcontrib>Qin, Jianbin</creatorcontrib><creatorcontrib>Hu, Yan</creatorcontrib><creatorcontrib>Wang, Di</creatorcontrib><title>GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings</title><title>arXiv.org</title><description>Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model training objective. To address this, we propose GARI that combines the distributional training objectives with multiple isomorphism losses guided by the graph attention network. GARI considers the impact of semantical variations of words in order to define the relative isomorphism of the embedding spaces. Experimental evaluation using the Arabic language data set shows that GARI outperforms the existing research by improving the average P@1 by a relative score of up to 40.95% and 76.80% for in-domain and domain mismatch settings respectively. We release the codes for GARI at https://github.com/asif6827/GARI.</description><subject>Embedding</subject><subject>Isomorphism</subject><subject>Training</subject><subject>Words (language)</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNykELgjAYgOERBEn5Hz7oLKzpanSTMPUqQUeZOXOi-2yb_f469AM6vYfnXZGAxfEhEgljGxI6N1BK2fHEOI8DUuRpVZ4ht3LuIfVeGa_RQIcWKjVKr98KSocT2rnXbgLsILWy0Q-4o20hmxrVtto83Y6sOzk6Ff66JftrdrsU0WzxtSjn6wEXa75UMyEoF4ngNP7v-gCvzzsU</recordid><startdate>20231019</startdate><enddate>20231019</enddate><creator>Ali, Muhammad Asif</creator><creator>Alshmrani, Maha</creator><creator>Qin, Jianbin</creator><creator>Hu, Yan</creator><creator>Wang, Di</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231019</creationdate><title>GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings</title><author>Ali, Muhammad Asif ; Alshmrani, Maha ; Qin, Jianbin ; Hu, Yan ; Wang, Di</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28805848503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Embedding</topic><topic>Isomorphism</topic><topic>Training</topic><topic>Words (language)</topic><toplevel>online_resources</toplevel><creatorcontrib>Ali, Muhammad Asif</creatorcontrib><creatorcontrib>Alshmrani, Maha</creatorcontrib><creatorcontrib>Qin, Jianbin</creatorcontrib><creatorcontrib>Hu, Yan</creatorcontrib><creatorcontrib>Wang, Di</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ali, Muhammad Asif</au><au>Alshmrani, Maha</au><au>Qin, Jianbin</au><au>Hu, Yan</au><au>Wang, Di</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings</atitle><jtitle>arXiv.org</jtitle><date>2023-10-19</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model training objective. To address this, we propose GARI that combines the distributional training objectives with multiple isomorphism losses guided by the graph attention network. GARI considers the impact of semantical variations of words in order to define the relative isomorphism of the embedding spaces. Experimental evaluation using the Arabic language data set shows that GARI outperforms the existing research by improving the average P@1 by a relative score of up to 40.95% and 76.80% for in-domain and domain mismatch settings respectively. We release the codes for GARI at https://github.com/asif6827/GARI.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2880584850
source Free E- Journals
subjects Embedding
Isomorphism
Training
Words (language)
title GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T13%3A29%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=GARI:%20Graph%20Attention%20for%20Relative%20Isomorphism%20of%20Arabic%20Word%20Embeddings&rft.jtitle=arXiv.org&rft.au=Ali,%20Muhammad%20Asif&rft.date=2023-10-19&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2880584850%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2880584850&rft_id=info:pmid/&rfr_iscdi=true