Special conference Mirko Degli Esposti

Entropy measures and natural language features of Artificial Intelligence generated texts

19.09.2019 - 19.09.2019

Mirko Degli Esposti is Professor of Mathematics, Vice-rector of University of Bologna, Italy, invited by the laboratory AGM

Recent developments of A.I. show an increasing capability of generating artificial media and art contents, with huge impact on the creativity Industry. After a brief introduction, we concentrate on automatic text generation. 

In particular, Long Short-Term Memory (LSTM) networks have recently shown remarkable performance in several tasks dealing with natural language generation, such as image captioning or poetry composition. 

Yet, only few works have analyzed text generated by LSTMs in order to quantitatively evaluate to which extent such artificial texts resemble those generated by humans. For LSTM networks a temperature-like parameter controlling the generation process shows an optimal value---for which the produced texts are closest (in a way we will explain) to real language---consistent across all the different entropic and statistical features investigated.

Date: Thursday 19th September from 12:30 to 14:00

Venue: Maison internationale de la recherche, Neuville-sur-Oise. Access to the MIR

To attend the Special conference, please subscribe