Unbalanced Optimal Transport for Unbalanced Word Alignment

Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-06
Main Authors: Arase, Yuki, Han, Bao, Yokoi, Sho
Format: Article
Language:English
Subjects:
Alignment
Semantics
Sentences
Words (language)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Arase, Yuki
Han, Bao
Yokoi, Sho
description Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2823796911</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2823796911</sourcerecordid><originalsourceid>FETCH-proquest_journals_28237969113</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwCs1LSsxJzEtOTVHwLyjJzE3MUQgpSswrLsgvKlFIyy9SQFIQnl-UouCYk5mel5uaV8LDwJqWmFOcyguluRmU3VxDnD10C4ryC0tTi0vis_JLi_KAUvFGFkbG5pZmloaGxsSpAgDCnDbe</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2823796911</pqid></control><display><type>article</type><title>Unbalanced Optimal Transport for Unbalanced Word Alignment</title><source>Publicly Available Content Database</source><creator>Arase, Yuki ; Han, Bao ; Yokoi, Sho</creator><creatorcontrib>Arase, Yuki ; Han, Bao ; Yokoi, Sho</creatorcontrib><description>Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Alignment ; Semantics ; Sentences ; Words (language)</subject><ispartof>arXiv.org, 2023-06</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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2823796911?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25731,36989,44566</link.rule.ids></links><search><creatorcontrib>Arase, Yuki</creatorcontrib><creatorcontrib>Han, Bao</creatorcontrib><creatorcontrib>Yokoi, Sho</creatorcontrib><title>Unbalanced Optimal Transport for Unbalanced Word Alignment</title><title>arXiv.org</title><description>Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.</description><subject>Alignment</subject><subject>Semantics</subject><subject>Sentences</subject><subject>Words (language)</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwCs1LSsxJzEtOTVHwLyjJzE3MUQgpSswrLsgvKlFIyy9SQFIQnl-UouCYk5mel5uaV8LDwJqWmFOcyguluRmU3VxDnD10C4ryC0tTi0vis_JLi_KAUvFGFkbG5pZmloaGxsSpAgDCnDbe</recordid><startdate>20230607</startdate><enddate>20230607</enddate><creator>Arase, Yuki</creator><creator>Han, Bao</creator><creator>Yokoi, Sho</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>20230607</creationdate><title>Unbalanced Optimal Transport for Unbalanced Word Alignment</title><author>Arase, Yuki ; Han, Bao ; Yokoi, Sho</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28237969113</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Alignment</topic><topic>Semantics</topic><topic>Sentences</topic><topic>Words (language)</topic><toplevel>online_resources</toplevel><creatorcontrib>Arase, Yuki</creatorcontrib><creatorcontrib>Han, Bao</creatorcontrib><creatorcontrib>Yokoi, Sho</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</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>Arase, Yuki</au><au>Han, Bao</au><au>Yokoi, Sho</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Unbalanced Optimal Transport for Unbalanced Word Alignment</atitle><jtitle>arXiv.org</jtitle><date>2023-06-07</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Monolingual word alignment is crucial to model semantic interactions between sentences. In particular, null alignment, a phenomenon in which words have no corresponding counterparts, is pervasive and critical in handling semantically divergent sentences. Identification of null alignment is useful on its own to reason about the semantic similarity of sentences by indicating there exists information inequality. To achieve unbalanced word alignment that values both alignment and null alignment, this study shows that the family of optimal transport (OT), i.e., balanced, partial, and unbalanced OT, are natural and powerful approaches even without tailor-made techniques. Our extensive experiments covering unsupervised and supervised settings indicate that our generic OT-based alignment methods are competitive against the state-of-the-arts specially designed for word alignment, remarkably on challenging datasets with high null alignment frequencies.</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, 2023-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_2823796911
source Publicly Available Content Database
subjects Alignment
Semantics
Sentences
Words (language)
title Unbalanced Optimal Transport for Unbalanced Word Alignment
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T23%3A21%3A12IST&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=Unbalanced%20Optimal%20Transport%20for%20Unbalanced%20Word%20Alignment&rft.jtitle=arXiv.org&rft.au=Arase,%20Yuki&rft.date=2023-06-07&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2823796911%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28237969113%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2823796911&rft_id=info:pmid/&rfr_iscdi=true