Quality estimation for text simplification

Štajner, Sanja ; Popović, Maja ; Béchara, Hanna

URL: https://www.researchgate.net/publication/301229460...
Additional URL: http://www.lrec-conf.org/proceedings/lrec2016/work...
Document Type: Conference or workshop publication
Year of publication: 2016
Book title: qats2016 : LREC 2016 Workshop & Shared Task on Quality Assessment for Text Simplification (QATS), 28th May 2016, Portorož, Slovenia ; proceedings
Page range: 15-21
Conference title: Qats2016
Location of the conference venue: Portorož, Slovenia
Date of the conference: 28 May 2016
Publisher: Štajner, Sanja
Place of publication: Paris
Publishing house: ELRA-ERDA
Publication language: English
Institution: School of Business Informatics and Mathematics > Semantic Web (Juniorprofessur) (Ponzetto 2013-2015)
School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
Subject: 004 Computer science, internet
Keywords (English): text simplification , quality assessment , sentence classification
Abstract: The quality of the output generated by automatic Text Simplification (TS) systems is traditionally assessed by human annotators. In spite of the fact that the automatisation of that process would enable faster and more consistent evaluation, there have been almost no studies addressing this problem. We propose several decision-making procedures for automatic classification of the simplified sentences into three classes (bad, OK, good) depending on their grammaticality, meaning preservation, and simplicity. We experiment with ten different classification algorithms and 12 different feature sets on three TS datasets obtained using different text simplification strategies, achieving the results significantly above the state of the art. Additionally, we propose to use an unique measure (Total2 or Total3) for classifying the quality of the automatically simplified sentences into two (discard or keep) or three (bad, OK, good) classes.
Additional information: Online-Ressource

Dieser Eintrag ist Teil der Universitätsbibliographie.

Metadata export


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item