liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Keeping an Eye on the Context: An Eye Tracking Study of Cohesion Errors in Automatic Text Summarization
Linköping University, Department of Computer and Information Science. Linköping University, Faculty of Arts and Sciences.
2013 (English)Independent thesis Basic level (degree of Bachelor), 12 credits / 18 HE creditsStudent thesisAlternative title
Med ett öga på sammanhanget : En ögonrörelsestudie av kohesionsfel i automatiska textsammanfattningar (Swedish)
Abstract [en]

Automatic text summarization is a growing field due to the modern world’s Internet based society, but to automatically create perfect summaries is not easy, and cohesion errors are common.

By the usage of an eye tracking camera, this thesis studies the nature of four different types of cohesion errors occurring in summaries. A total of 23 participants read and rated four different texts and marked the most difficult areas of each text.

Statistical analysis of the data revealed that absent cohesion or context and broken anaphoric reference (pronouns) caused some disturbance in reading, but that the impact is restricted to the effort to read rather than the comprehension of the text. Erroneous anaphoric reference (pronouns) was not detected by the participants which poses a problem for automatic text summarizers, and other potential disturbing factors were detected.

Finally, the question of the meaningfulness of keeping absent cohesion or context as a separate error type was raised. 

Place, publisher, year, edition, pages
2013. , 37 p.
Keyword [en]
Automatic text summarization, cohesion errors, eye tracking, CogSum
National Category
Language Technology (Computational Linguistics)
URN: urn:nbn:se:liu:diva-95527ISRN: LIU-IDA/KOGVET-G--13/028--SEOAI: diva2:635836
Subject / course
Cognitive science programme
Available from: 2013-08-12 Created: 2013-07-05 Last updated: 2013-08-12Bibliographically approved

Open Access in DiVA

fulltext(377 kB)118 downloads
File information
File name FULLTEXT01.pdfFile size 377 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Rennes, Evelina
By organisation
Department of Computer and Information ScienceFaculty of Arts and Sciences
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar
Total: 118 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 270 hits
ReferencesLink to record
Permanent link

Direct link