I
Ivano Lauriola
Researcher at University of Padua
Publications - 34
Citations - 290
Ivano Lauriola is an academic researcher from University of Padua. The author has contributed to research in topics: Multiple kernel learning & Computer science. The author has an hindex of 6, co-authored 29 publications receiving 98 citations. Previous affiliations of Ivano Lauriola include Amazon.com & fondazione bruno kessler.
Papers
More filters
Journal ArticleDOI
An introduction to Deep Learning in Natural Language Processing: Models, techniques, and tools
TL;DR: A survey of the application of deep learning techniques in NLP, with a focus on the various tasks where deep learning is demonstrating stronger impact.
Journal ArticleDOI
Enhancing deep neural networks via multiple kernel learning
TL;DR: This paper introduces a general framework in which the internal representations computed by a deep neural network are optimally combined by means of Multiple Kernel Learning, and is instantiated for Multi-layer Perceptrons architectures, and for Convolutional Neural Networks.
Book ChapterDOI
Answer Sentence Selection Using Local and Global Context in Transformer Models
TL;DR: The authors analyzed the role of contextual information for the sentence selection task in Transformer based architectures, leveraging two types of context, local and global, and showed that the combination of the local context and global context in a Transformer model significantly improves the accuracy in answer sentence selection.
Proceedings Article
DecOp: A Multilingual and Multi-domain Corpus For Detecting Deception In Typed Text.
TL;DR: DecOp (Deceptive Opinions), a new language resource developed for automatic deception detection in cross-domain and cross-language scenarios, is introduced and the collection procedure of the DecOp corpus and his main characteristics are described.
Book ChapterDOI
Radius-Margin Ratio Optimization for Dot-Product Boolean Kernel Learning
TL;DR: It is demonstrated that, under mild conditions, any dot-product kernel defined on binary valued data can be seen as a linear non-negative combination of boolean kernels, specifically, monotone conjunctive kernels (mC-kernels) with different degrees.