no code implementations • 30 Jun 2020 • Erion Çano, Maurizio Morisio
Our results indicate that parallel convolutions of filter lengths up to three are usually enough for capturing relevant text features.
no code implementations • 25 Jun 2020 • Erion Çano, Riccardo Coppola, Eleonora Gargiulo, Marco Marengo, Maurizio Morisio
Driving and music listening are two inseparable everyday activities for millions of people today in the world.
1 code implementation • LREC 2020 • Matteo Antonio Senese, Giuseppe Rizzo, Mauro Dragoni, Maurizio Morisio
In the last years, the state of the art of NLP research has made a huge step forward.
no code implementations • 6 Mar 2020 • Erion Çano, Maurizio Morisio
Quality of word embeddings and performance of their applications depends on several factors like training method, corpus size and relevance etc.
1 code implementation • 8 Feb 2020 • Andrea Fiandro, Giorgio Crepaldi, Diego Monti, Giuseppe Rizzo, Maurizio Morisio
This paper describes the solution of the POLINKS team to the RecSys Challenge 2019 that focuses on the task of predicting the last click-out in a session-based interaction.
no code implementations • 2 Sep 2019 • Diego Monti, Giuseppe Rizzo, Maurizio Morisio
The public availability of collections containing user preferences is of vital importance for performing offline evaluations in the field of recommender systems.
no code implementations • 2 Feb 2019 • Erion Çano, Maurizio Morisio
This work investigates the role of factors like training method, training corpus size and thematic relevance of texts in the performance of word embedding features on sentiment analysis of tweets, song lyrics, movie reviews and item reviews.
1 code implementation • 12 Jan 2019 • Erion Çano, Maurizio Morisio
Also cold-start and data sparsity are the two traditional and top problems being addressed in 23 and 22 studies each, while movies and movie datasets are still widely used by most of the authors.
1 code implementation • 11 Oct 2018 • Diego Monti, Enrico Palumbo, Giuseppe Rizzo, Maurizio Morisio
In this paper, we present sequeval, a software tool capable of performing the offline evaluation of a recommender system designed to suggest a sequence of items.
1 code implementation • 11 Oct 2018 • Diego Monti, Giuseppe Rizzo, Maurizio Morisio
For these reasons, we introduce RecLab, an open source software for evaluating recommender systems in a distributed fashion.