A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language

Giosue' Lo Bosco, Giovanni Pilato, Daniele Schicchi, Giovanni Pilato

Risultato della ricerca: Conference contribution

4 Citazioni (Scopus)

Abstract

Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS. We have also provided a comparison of our model with a state of the art methodused for the same purpose
Lingua originaleEnglish
Titolo della pubblicazione ospiteAIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition
Pagine90-97
Numero di pagine8
Stato di pubblicazionePublished - 2019

Serie di pubblicazioni

NomeCEUR WORKSHOP PROCEEDINGS

Fingerprint

Decision making
Processing
Experiments
Deep neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cita questo

Lo Bosco, G., Pilato, G., Schicchi, D., & Pilato, G. (2019). A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language. In AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition (pagg. 90-97). (CEUR WORKSHOP PROCEEDINGS).

A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language. / Lo Bosco, Giosue'; Pilato, Giovanni; Schicchi, Daniele; Pilato, Giovanni.

AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition. 2019. pag. 90-97 (CEUR WORKSHOP PROCEEDINGS).

Risultato della ricerca: Conference contribution

Lo Bosco, G, Pilato, G, Schicchi, D & Pilato, G 2019, A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language. in AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition. CEUR WORKSHOP PROCEEDINGS, pagg. 90-97.
Lo Bosco G, Pilato G, Schicchi D, Pilato G. A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language. In AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition. 2019. pag. 90-97. (CEUR WORKSHOP PROCEEDINGS).
Lo Bosco, Giosue' ; Pilato, Giovanni ; Schicchi, Daniele ; Pilato, Giovanni. / A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language. AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition. 2019. pagg. 90-97 (CEUR WORKSHOP PROCEEDINGS).
@inproceedings{71f113dd1cde4d0aa040d613943b7b86,
title = "A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language",
abstract = "Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS. We have also provided a comparison of our model with a state of the art methodused for the same purpose",
author = "{Lo Bosco}, Giosue' and Giovanni Pilato and Daniele Schicchi and Giovanni Pilato",
year = "2019",
language = "English",
series = "CEUR WORKSHOP PROCEEDINGS",
pages = "90--97",
booktitle = "AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition",

}

TY - GEN

T1 - A Recurrent Deep Neural Network Model to measure Sentence Complexity for the Italian Language

AU - Lo Bosco, Giosue'

AU - Pilato, Giovanni

AU - Schicchi, Daniele

AU - Pilato, Giovanni

PY - 2019

Y1 - 2019

N2 - Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS. We have also provided a comparison of our model with a state of the art methodused for the same purpose

AB - Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS. We have also provided a comparison of our model with a state of the art methodused for the same purpose

UR - http://hdl.handle.net/10447/366497

UR - http://ceur-ws.org/Vol-2418/paper10.pdf

M3 - Conference contribution

T3 - CEUR WORKSHOP PROCEEDINGS

SP - 90

EP - 97

BT - AIC 2018, Artificial Intelligence and Cognition 2018 - Proceedings of the 6th International Workshop on Artificial Intelligence and Cognition

ER -