No Cover Image

Journal article 207 views 50 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!
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.
Keywords: Text alignment, parallel translations, text visualization
College: College of Science
Issue: 4
Start Page: 245
End Page: 262