Improving Downstream Task Performance by Treating Numbers as Entities

Improving Downstream Task Performance by Treating Numbers as Entities

Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP mode...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-09
Hauptverfasser: Dhanasekar Sundararaman, Subramanian, Vivek, Wang, Guoyin, Xu, Liyan, Lawrence, Carin
Format: Artikel
Sprache:eng
Schlagworte:
Classification
Natural language processing
Numeracy
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 Dhanasekar Sundararaman
Subramanian, Vivek
Wang, Guoyin
Xu, Liyan
Lawrence, Carin
description Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. In this work, we attempt to tap this potential of state-of-the-art NLP models and transfer their ability to boost performance in related tasks. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) task and on question answering using joint embeddings, outperforming the BERT and RoBERTa baseline classification.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2661735057</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2661735057</sourcerecordid><originalsourceid>FETCH-proquest_journals_26617350573</originalsourceid><addsrcrecordid>eNqNjLEKwjAUAIMgWLT_8MC5kCamddeKLuLQvaTyKq0m0bxU8e-N4Ac43XDHTVgipMyz9UqIGUuJBs65KEqhlExYdTB37569vcDWvSwFj9pArekKJ_Sd80bbM0L7hjqa8O2Oo2nRE2iCyoY-9EgLNu30jTD9cc6Wu6re7LP4foxIoRnc6G1UjSiKvJSKq1L-V30Al_k7EA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2661735057</pqid></control><display><type>article</type><title>Improving Downstream Task Performance by Treating Numbers as Entities</title><source>Free E- Journals</source><creator>Dhanasekar Sundararaman ; Subramanian, Vivek ; Wang, Guoyin ; Xu, Liyan ; Lawrence, Carin</creator><creatorcontrib>Dhanasekar Sundararaman ; Subramanian, Vivek ; Wang, Guoyin ; Xu, Liyan ; Lawrence, Carin</creatorcontrib><description>Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. In this work, we attempt to tap this potential of state-of-the-art NLP models and transfer their ability to boost performance in related tasks. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) task and on question answering using joint embeddings, outperforming the BERT and RoBERTa baseline classification.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Classification ; Natural language processing ; Numeracy</subject><ispartof>arXiv.org, 2022-09</ispartof><rights>2022. 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>780,784</link.rule.ids></links><search><creatorcontrib>Dhanasekar Sundararaman</creatorcontrib><creatorcontrib>Subramanian, Vivek</creatorcontrib><creatorcontrib>Wang, Guoyin</creatorcontrib><creatorcontrib>Xu, Liyan</creatorcontrib><creatorcontrib>Lawrence, Carin</creatorcontrib><title>Improving Downstream Task Performance by Treating Numbers as Entities</title><title>arXiv.org</title><description>Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. In this work, we attempt to tap this potential of state-of-the-art NLP models and transfer their ability to boost performance in related tasks. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) task and on question answering using joint embeddings, outperforming the BERT and RoBERTa baseline classification.</description><subject>Classification</subject><subject>Natural language processing</subject><subject>Numeracy</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjLEKwjAUAIMgWLT_8MC5kCamddeKLuLQvaTyKq0m0bxU8e-N4Ac43XDHTVgipMyz9UqIGUuJBs65KEqhlExYdTB37569vcDWvSwFj9pArekKJ_Sd80bbM0L7hjqa8O2Oo2nRE2iCyoY-9EgLNu30jTD9cc6Wu6re7LP4foxIoRnc6G1UjSiKvJSKq1L-V30Al_k7EA</recordid><startdate>20220918</startdate><enddate>20220918</enddate><creator>Dhanasekar Sundararaman</creator><creator>Subramanian, Vivek</creator><creator>Wang, Guoyin</creator><creator>Xu, Liyan</creator><creator>Lawrence, Carin</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>20220918</creationdate><title>Improving Downstream Task Performance by Treating Numbers as Entities</title><author>Dhanasekar Sundararaman ; Subramanian, Vivek ; Wang, Guoyin ; Xu, Liyan ; Lawrence, Carin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26617350573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Classification</topic><topic>Natural language processing</topic><topic>Numeracy</topic><toplevel>online_resources</toplevel><creatorcontrib>Dhanasekar Sundararaman</creatorcontrib><creatorcontrib>Subramanian, Vivek</creatorcontrib><creatorcontrib>Wang, Guoyin</creatorcontrib><creatorcontrib>Xu, Liyan</creatorcontrib><creatorcontrib>Lawrence, Carin</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>Dhanasekar Sundararaman</au><au>Subramanian, Vivek</au><au>Wang, Guoyin</au><au>Xu, Liyan</au><au>Lawrence, Carin</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Improving Downstream Task Performance by Treating Numbers as Entities</atitle><jtitle>arXiv.org</jtitle><date>2022-09-18</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. In this work, we attempt to tap this potential of state-of-the-art NLP models and transfer their ability to boost performance in related tasks. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) task and on question answering using joint embeddings, outperforming the BERT and RoBERTa baseline classification.</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, 2022-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2661735057
source Free E- Journals
subjects Classification
Natural language processing
Numeracy
title Improving Downstream Task Performance by Treating Numbers as Entities
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T17%3A49%3A18IST&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=Improving%20Downstream%20Task%20Performance%20by%20Treating%20Numbers%20as%20Entities&rft.jtitle=arXiv.org&rft.au=Dhanasekar%20Sundararaman&rft.date=2022-09-18&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2661735057%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2661735057&rft_id=info:pmid/&rfr_iscdi=true