An Analysis of Word2Vec for the Italian Language

Authors :: Di Gennaro, Giovanni
Buonanno, Amedeo
Di Girolamo, Antonio
Ospedale, Armando
Palmieri, Francesco A. N.
Fedele, Gianfranco
Source :: Progresses in Artificial Intelligence and Neural Systems. Smart Innovation, Systems and Technologies, vol 184. Springer, Singapore - First Online: July 2020
Publication Year :: 2020
Abstract: Word representation is fundamental in NLP tasks, because it is precisely from the coding of semantic closeness between words that it is possible to think of teaching a machine to understand text. Despite the spread of word embedding concepts, still few are the achievements in linguistic contexts other than English. In this work, analysing the semantic capacity of the Word2Vec algorithm, an embedding for the Italian language is produced. Parameter setting such as the number of epochs, the size of the context window and the number of negatively backpropagated samples is explored.<br />Comment: Presented at the 2019 Italian Workshop on Neural Networks (WIRN'19) - June 2019

Subjects :: Computer Science - Computation and Language
Computer Science - Machine Learning
Statistics - Machine Learning

Database :: arXiv
Journal :: Progresses in Artificial Intelligence and Neural Systems. Smart Innovation, Systems and Technologies, vol 184. Springer, Singapore - First Online: July 2020
Publication Type :: Report
Accession number :: edsarx.2001.09332
Document Type :: Working Paper
Full Text :: https://doi.org/10.1007/978-981-15-5093-5_13