Contributo in atti di convegno, 2014, ENG

Assessing the readability of sentences: which corpora and features?

Dell'Orletta F., Wieling M., Cimino A., Venturi G., Montemagni S.

Istituto di Linguistica Computazionale "Antonio Zampolli" (ILC-CNR); Department of Humanities Computing, University of Groningen, The Netherlands; Department of Quantitative Linguistics, University of Tubingen, Germany

The paper investigates the problem of sentence readability assessment, which is modelled as a classification task, with a specific view to text simplification. In particular, it addresses two open issues connected with it, i.e. the corpora to be used for training, and the identification of the most effective features to determine sentence readability. An existing readability assessment tool developed for Italian was specialized at the level of training corpus and learning algorithm. A maximum entropy-based feature selection and ranking algorithm (grafting) was used to identify to the most relevant features: it turned out that assessing the readability of sentences is a complex task, requiring a high number of features, mainly syntactic ones.

9th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2014), pp. 163–173, Baltimore, Maryland, USA, 26 giugno 2014

Keywords

CNR authors

Venturi Giulia, Cimino Andrea, Montemagni Simonetta, Dell Orletta Felice

CNR institutes

ILC – Istituto di linguistica computazionale "Antonio Zampolli"

ID: 294084

Year: 2014

Type: Contributo in atti di convegno

Creation: 2015-01-13 13:08:28.000

Last update: 2023-11-06 19:33:17.000

External links

OAI-PMH: Dublin Core

OAI-PMH: Mods

OAI-PMH: RDF

URL: http://acl2014.org/acl2014/W14-18/pdf/W14-1820.pdf

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:294084