no code implementations • WS 2016 • Johan Falkenjack, Arne J{\"o}nsson
Data driven approaches to readability analysis for languages other than English has been plagued by a scarcity of suitable corpora.
no code implementations • WS 2016 • Sarah Albertsson, Evelina Rennes, Arne J{\"o}nsson
The first method (M1) was originally developed for the task of text reuse detection, measuring sentence similarity by a modified version of a TF-IDF vector space model.
no code implementations • LREC 2014 • Evelina Rennes, Arne J{\"o}nsson
By the usage of an eye tracking camera, we have studied the nature of four different types of cohesion errors occurring in extraction based summaries.
no code implementations • LREC 2012 • Christian Smith, Henrik Danielsson, Arne J{\"o}nsson
We have investigated the effect on summary quality when using various language resources to train a vector space based extraction summarizer.
no code implementations • LREC 2012 • Thomas Kaspersson, Christian Smith, Henrik Danielsson, Arne J{\"o}nsson
These results show that the degree of summarization has to be taken into account to minimize the amount of errors by extraction based summarizers.