Improving Multi-Head Attention with Capsule Networks

Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gu, Shuhao, Feng, Yang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Gu, Shuhao
Feng, Yang
description Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering and separating. We conducted experiments on Chinese-to-English and English-to-German translation tasks and got consistent improvements over the strong Transformer baseline.
doi_str_mv 10.48550/arxiv.1909.00188
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1909_00188</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1909_00188</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-17364f1f4dd4b54223685d7164c18ae15d9be31aba7c7685280436b5f2dc9beb3</originalsourceid><addsrcrecordid>eNotzr1uwjAYhWEvHSroBXSqbyCpv_g3I4raggTtwh59jh2wCEnkGGjvvhQ6neGVjh5CnoHlwkjJXjF-h3MOJStzxsCYRyJWxzEO59Dv6ObUpZAtPTq6SMn3KQw9vYS0pxWO06nz9NOnyxAP05w8tNhN_ul_Z2T7_ratltn662NVLdYZKm0y0FyJFlrhnLBSFAVXRjoNSjRg0IN0pfUc0KJu9DUVhgmurGwL11yL5TPycr-9sesxhiPGn_qPX9_4_BdK8D86</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Improving Multi-Head Attention with Capsule Networks</title><source>arXiv.org</source><creator>Gu, Shuhao ; Feng, Yang</creator><creatorcontrib>Gu, Shuhao ; Feng, Yang</creatorcontrib><description>Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering and separating. We conducted experiments on Chinese-to-English and English-to-German translation tasks and got consistent improvements over the strong Transformer baseline.</description><identifier>DOI: 10.48550/arxiv.1909.00188</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2019-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1909.00188$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1909.00188$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Gu, Shuhao</creatorcontrib><creatorcontrib>Feng, Yang</creatorcontrib><title>Improving Multi-Head Attention with Capsule Networks</title><description>Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering and separating. We conducted experiments on Chinese-to-English and English-to-German translation tasks and got consistent improvements over the strong Transformer baseline.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr1uwjAYhWEvHSroBXSqbyCpv_g3I4raggTtwh59jh2wCEnkGGjvvhQ6neGVjh5CnoHlwkjJXjF-h3MOJStzxsCYRyJWxzEO59Dv6ObUpZAtPTq6SMn3KQw9vYS0pxWO06nz9NOnyxAP05w8tNhN_ul_Z2T7_ratltn662NVLdYZKm0y0FyJFlrhnLBSFAVXRjoNSjRg0IN0pfUc0KJu9DUVhgmurGwL11yL5TPycr-9sesxhiPGn_qPX9_4_BdK8D86</recordid><startdate>20190831</startdate><enddate>20190831</enddate><creator>Gu, Shuhao</creator><creator>Feng, Yang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190831</creationdate><title>Improving Multi-Head Attention with Capsule Networks</title><author>Gu, Shuhao ; Feng, Yang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-17364f1f4dd4b54223685d7164c18ae15d9be31aba7c7685280436b5f2dc9beb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Gu, Shuhao</creatorcontrib><creatorcontrib>Feng, Yang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gu, Shuhao</au><au>Feng, Yang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving Multi-Head Attention with Capsule Networks</atitle><date>2019-08-31</date><risdate>2019</risdate><abstract>Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering and separating. We conducted experiments on Chinese-to-English and English-to-German translation tasks and got consistent improvements over the strong Transformer baseline.</abstract><doi>10.48550/arxiv.1909.00188</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1909.00188
ispartof
issn
language eng
recordid cdi_arxiv_primary_1909_00188
source arXiv.org
subjects Computer Science - Computation and Language
title Improving Multi-Head Attention with Capsule Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T11%3A49%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20Multi-Head%20Attention%20with%20Capsule%20Networks&rft.au=Gu,%20Shuhao&rft.date=2019-08-31&rft_id=info:doi/10.48550/arxiv.1909.00188&rft_dat=%3Carxiv_GOX%3E1909_00188%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true