Victor Guimarães

Victor Guimarães, Vítor Santos Costa

Application domains that require considering relationships among objects which have real-valued attributes are becoming even more important. In this paper we propose NeuralLog, a first-order logic language that is compiled to a neural network. The main goal of NeuralLog is to bridge logic programming and deep learning, allowing advances in both fields to be combined in order to obtain better machine learning models. The main advantages of NeuralLog are: to allow neural networks to be defined as logic programs; and to be able to handle numeric attributes and functions. We compared NeuralLog with two distinct systems that use first-order logic to build neural networks. We have also shown that NeuralLog can learn link prediction and classification tasks, using the same theory as the compared systems, achieving better results for the area under the ROC curve in four datasets: Cora and UWCSE for link prediction; and Yelp and PAKDD15 for classification; and comparable results for link prediction in the WordNet dataset.

Luciano Barbosa, Paulo R. Cavalin, Victor Guimaraes et al.

In this paper, we present the methodology and the results obtained by our teams, dubbed Blue Man Group, in the ASSIN (from the Portuguese {\it Avaliação de Similaridade Semântica e Inferência Textual}) competition, held at PROPOR 2016\footnote{International Conference on the Computational Processing of the Portuguese Language - http://propor2016.di.fc.ul.pt/}. Our team's strategy consisted of evaluating methods based on semantic word vectors, following two distinct directions: 1) to make use of low-dimensional, compact, feature sets, and 2) deep learning-based strategies dealing with high-dimensional feature vectors. Evaluation results demonstrated that the first strategy was more promising, so that the results from the second strategy have been discarded. As a result, by considering the best run of each of the six teams, we have been able to achieve the best accuracy and F1 values in entailment recognition, in the Brazilian Portuguese set, and the best F1 score overall. In the semantic similarity task, our team was ranked second in the Brazilian Portuguese set, and third considering both sets.