Istituto di Scienza e Tecnologie dell'Informazione     
Berardi G., Esuli A., Marcheggiani D. Word Embeddings Go to Italy: A Comparison of Models and Training Datasets. In: IIR - 6th Italian Information Retrieval Workshop (Cagliari, Italy, 25-26 May 2015). Atti, article n. 11. Paolo Boldi, Reffaele Perego, Fabrizio Sebastiani (eds.). (CEUR Workshop Proceedings, vol. 1404). CEUR-WS.org, 2015.
In this paper we present some preliminary results on the generation of word embeddings for the Italian language. We compare two popular word representation models, word2vec and GloVe, and train them on two datasets with different stylistic properties. We test the generated word embeddings on a word analogy test derived from the one originally proposed for word2vec, adapted to capture some of the linguistic aspects that are specific of Italian. Results show that the tested models are able to create syntactically and semantically meaningful word embeddings despite the higher morphological complexity of Italian with respect to English. Moreover, we have found that the stylistic properties of the training dataset plays a relevant role in the type of information captured by the produced vectors.
URL: http://ceur-ws.org/Vol-1404/
Subject word2vec
word embeddings
I.2.6 Learning

Icona documento 1) Download Document PDF

Icona documento Open access Icona documento Restricted Icona documento Private


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional