No Cover Image

Journal article 231 views 64 downloads

VNLP: Visible natural language processing

Mohammad Alharbi Alharbi, Matt Roach Orcid Logo, Tom Cheesman, Bob Laramee Orcid Logo

Information Visualization, Volume: 20, Issue: 4, Pages: 245 - 262

Swansea University Authors: Mohammad Alharbi Alharbi, Matt Roach Orcid Logo, Tom Cheesman, Bob Laramee Orcid Logo

  • 57876.pdf

    PDF | Version of Record

    © The Author(s) 2021. This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License

    Download (3.43MB)

Abstract

In general, Natural Language Processing (NLP) algorithms exhibit black- box behavior.Users input text and output is provided with no explanation of how the results are obtained.In order to increase understanding and trust, users value transparent processing which may explain derived results and enab...

Full description

Published in: Information Visualization
ISSN: 1473-8716 1473-8724
Published: SAGE Publications 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57876
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-09-13T15:28:47Z
last_indexed 2021-10-07T03:22:28Z
id cronfa57876
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-10-06T14:14:26.6271273</datestamp><bib-version>v2</bib-version><id>57876</id><entry>2021-09-13</entry><title>VNLP: Visible natural language processing</title><swanseaauthors><author><sid>2c535a171da53c1407e75854f46eeb76</sid><firstname>Mohammad Alharbi</firstname><surname>Alharbi</surname><name>Mohammad Alharbi Alharbi</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>9722c301d5bbdc96e967cdc629290fec</sid><ORCID>0000-0002-1486-5537</ORCID><firstname>Matt</firstname><surname>Roach</surname><name>Matt Roach</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b7304d4beb9e6e86ed66575a61157476</sid><firstname>Tom</firstname><surname>Cheesman</surname><name>Tom Cheesman</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>7737f06e2186278a925f6119c48db8b1</sid><ORCID>0000-0002-3874-6145</ORCID><firstname>Bob</firstname><surname>Laramee</surname><name>Bob Laramee</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-09-13</date><deptcode>SCS</deptcode><abstract>In general, Natural Language Processing (NLP) algorithms exhibit black- box behavior.Users input text and output is provided with no explanation of how the results are obtained.In order to increase understanding and trust, users value transparent processing which may explain derived results and enable understanding of the underlying routines.Many approaches take an opaque approach by default when designing NLP tools and do not incorporate a means to steer and manipulate the intermediate NLP steps.We present an interactive, customizable, visual framework that enables users to observe and participate in the NLP pipeline processes, explicitly manipulate the parameters of each step, and explore the result visually based on user preferences. The visible NLP (VNLP) design is applied to a text similarity application to demonstrate the utility and advantages of a visible and transparent NLP pipeline in supporting users to understand and justify both the process and results. We also report feedback on our framework from a modern languages expert.</abstract><type>Journal Article</type><journal>Information Visualization</journal><volume>20</volume><journalNumber>4</journalNumber><paginationStart>245</paginationStart><paginationEnd>262</paginationEnd><publisher>SAGE Publications</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1473-8716</issnPrint><issnElectronic>1473-8724</issnElectronic><keywords>Text alignment, parallel translations, text visualization</keywords><publishedDay>1</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-10-01</publishedDate><doi>10.1177/14738716211038898</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-10-06T14:14:26.6271273</lastEdited><Created>2021-09-13T16:25:30.6699511</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Mohammad Alharbi</firstname><surname>Alharbi</surname><order>1</order></author><author><firstname>Matt</firstname><surname>Roach</surname><orcid>0000-0002-1486-5537</orcid><order>2</order></author><author><firstname>Tom</firstname><surname>Cheesman</surname><order>3</order></author><author><firstname>Bob</firstname><surname>Laramee</surname><orcid>0000-0002-3874-6145</orcid><order>4</order></author></authors><documents><document><filename>57876__21102__612912f75a7b43e2b6f1fcbb28531b78.pdf</filename><originalFilename>57876.pdf</originalFilename><uploaded>2021-10-06T14:12:23.2782533</uploaded><type>Output</type><contentLength>3601318</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2021. This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by-nc/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-10-06T14:14:26.6271273 v2 57876 2021-09-13 VNLP: Visible natural language processing 2c535a171da53c1407e75854f46eeb76 Mohammad Alharbi Alharbi Mohammad Alharbi Alharbi true false 9722c301d5bbdc96e967cdc629290fec 0000-0002-1486-5537 Matt Roach Matt Roach true false b7304d4beb9e6e86ed66575a61157476 Tom Cheesman Tom Cheesman true false 7737f06e2186278a925f6119c48db8b1 0000-0002-3874-6145 Bob Laramee Bob Laramee true false 2021-09-13 SCS In general, Natural Language Processing (NLP) algorithms exhibit black- box behavior.Users input text and output is provided with no explanation of how the results are obtained.In order to increase understanding and trust, users value transparent processing which may explain derived results and enable understanding of the underlying routines.Many approaches take an opaque approach by default when designing NLP tools and do not incorporate a means to steer and manipulate the intermediate NLP steps.We present an interactive, customizable, visual framework that enables users to observe and participate in the NLP pipeline processes, explicitly manipulate the parameters of each step, and explore the result visually based on user preferences. The visible NLP (VNLP) design is applied to a text similarity application to demonstrate the utility and advantages of a visible and transparent NLP pipeline in supporting users to understand and justify both the process and results. We also report feedback on our framework from a modern languages expert. Journal Article Information Visualization 20 4 245 262 SAGE Publications 1473-8716 1473-8724 Text alignment, parallel translations, text visualization 1 10 2021 2021-10-01 10.1177/14738716211038898 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2021-10-06T14:14:26.6271273 2021-09-13T16:25:30.6699511 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Mohammad Alharbi Alharbi 1 Matt Roach 0000-0002-1486-5537 2 Tom Cheesman 3 Bob Laramee 0000-0002-3874-6145 4 57876__21102__612912f75a7b43e2b6f1fcbb28531b78.pdf 57876.pdf 2021-10-06T14:12:23.2782533 Output 3601318 application/pdf Version of Record true © The Author(s) 2021. This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License true eng https://creativecommons.org/licenses/by-nc/4.0/
title VNLP: Visible natural language processing
spellingShingle VNLP: Visible natural language processing
Mohammad Alharbi Alharbi
Matt Roach
Tom Cheesman
Bob Laramee
title_short VNLP: Visible natural language processing
title_full VNLP: Visible natural language processing
title_fullStr VNLP: Visible natural language processing
title_full_unstemmed VNLP: Visible natural language processing
title_sort VNLP: Visible natural language processing
author_id_str_mv 2c535a171da53c1407e75854f46eeb76
9722c301d5bbdc96e967cdc629290fec
b7304d4beb9e6e86ed66575a61157476
7737f06e2186278a925f6119c48db8b1
author_id_fullname_str_mv 2c535a171da53c1407e75854f46eeb76_***_Mohammad Alharbi Alharbi
9722c301d5bbdc96e967cdc629290fec_***_Matt Roach
b7304d4beb9e6e86ed66575a61157476_***_Tom Cheesman
7737f06e2186278a925f6119c48db8b1_***_Bob Laramee
author Mohammad Alharbi Alharbi
Matt Roach
Tom Cheesman
Bob Laramee
author2 Mohammad Alharbi Alharbi
Matt Roach
Tom Cheesman
Bob Laramee
format Journal article
container_title Information Visualization
container_volume 20
container_issue 4
container_start_page 245
publishDate 2021
institution Swansea University
issn 1473-8716
1473-8724
doi_str_mv 10.1177/14738716211038898
publisher SAGE Publications
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description In general, Natural Language Processing (NLP) algorithms exhibit black- box behavior.Users input text and output is provided with no explanation of how the results are obtained.In order to increase understanding and trust, users value transparent processing which may explain derived results and enable understanding of the underlying routines.Many approaches take an opaque approach by default when designing NLP tools and do not incorporate a means to steer and manipulate the intermediate NLP steps.We present an interactive, customizable, visual framework that enables users to observe and participate in the NLP pipeline processes, explicitly manipulate the parameters of each step, and explore the result visually based on user preferences. The visible NLP (VNLP) design is applied to a text similarity application to demonstrate the utility and advantages of a visible and transparent NLP pipeline in supporting users to understand and justify both the process and results. We also report feedback on our framework from a modern languages expert.
published_date 2021-10-01T04:10:03Z
_version_ 1756781508255809536
score 10.928156