Please use this identifier to cite or link to this item: doi:10.22028/D291-30983
Volltext verfügbar? / Dokumentlieferung
Title: Psycholinguistic Models of Sentence Processing Improve Sentence Readability Ranking
Author(s): Howcroft, David M.
Demberg, Vera
Editor(s): Kunnemann, Florian
Iñurrieta, Uxoa
Camilleri, John J.
Coll Ardanuy, Mariona
Language: English
Title: European Chapter of the Association for Computational Linguistics - proceedings of the Student Research Workshop
Startpage: 958
Endpage: 968
Publisher/Platform: ACL
Year of Publication: 2017
Place of publication: Stroudsburg, PA
Title of the Conference: EACL 2017
Place of the conference: Valencia, Spain
Publikation type: Conference Paper
Abstract: While previous research on readability has typically focused on document-level measures, recent work in areas such as natural language generation has pointed out the need of sentence-level readability measures. Much of psycholinguistics has focused for many years on processing measures that provide difficulty estimates on a word-by-word basis. However, these psycholinguistic measures have not yet been tested on sentence readability ranking tasks. In this paper, we use four psycholinguistic measures: idea density, surprisal, integration cost, and embedding depth to test whether these features are predictive of readability levels. We find that psycholinguistic features significantly improve performance by up to 3 percentage points over a standard document-level readability metric baseline.
DOI of the first publication: 10.18653/v1/E17-1090
URL of the first publication:
Link to this record: hdl:20.500.11880/29718
ISBN: 978-1-945626-37-1
Date of registration: 23-Sep-2020
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Informatik
Professorship: MI - Prof. Dr. Vera Demberg
Collections:UniBib – Die Universitätsbibliographie

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.