Marcelo Finger


pdf bib
A logical-based corpus for cross-lingual evaluation
Felipe Salvatore | Marcelo Finger | Roberto Hirata Jr
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)

At present, different deep learning models are presenting high accuracy on popular inference datasets such as SNLI, MNLI, and SciTail. However, there are different indicators that those datasets can be exploited by using some simple linguistic patterns. This fact poses difficulties to our understanding of the actual capacity of machine learning models to solve the complex task of textual inference. We propose a new set of syntactic tasks focused on contradiction detection that require specific capacities over linguistic logical forms such as: Boolean coordination, quantifiers, definite description, and counting operators. We evaluate two kinds of deep learning models that implicitly exploit language structure: recurrent models and the Transformer network BERT. We show that although BERT is clearly more efficient to generalize over most logical forms, there is space for improvement when dealing with counting operators. Since the syntactic tasks can be implemented in different languages, we show a successful case of cross-lingual transfer learning between English and Portuguese.


pdf bib
Improving CoGrOO: the Brazilian Portuguese Grammar Checker
William D. Colen M. Silva | Marcelo Finger
Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology


pdf bib
Resolução da Heterogeneidade na Identificação de Pacientes (Resolution of Heterogeneity in the Identification of Patients) [in Portuguese]
Fábio Filocomo | Marcelo Finger | Diogo F. C. Patrão
Proceedings of the 8th Brazilian Symposium in Information and Human Language Technology


pdf bib
Variable-Length Markov Models and Ambiguous Words in Portuguese
Fabio Natanael Kepler | Marcelo Finger
Proceedings of the NAACL HLT 2010 Young Investigators Workshop on Computational Approaches to Languages of the Americas