Allan de Barcelos Silva

Allan de Barcelos Silva

Auto-generated profile, based on publicly available information

Allan de Barcelos Silva

Universidade do Vale do Rio dos Sinos – UNISINOS

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2020 in Expert Systems with Applications
Verified
Journal Article
Closed access
ASAllan de Barcelos Silva
Allan de Barcelos Silva
MGMarcio Miguel Gomes
Marcio Miguel Gomes
Cristiano da CostaCristiano da Costa
Cristiano da Costa
RRRodrigo da Rosa Righi
Rodrigo da Rosa Righi
Jorge BarbosaJorge Barbosa
Jorge Barbosa
GFGustavo Federizzi
Gustavo Federizzi

18 October 2019
Verified
Book Chapter
Closed access
PDF file
WOWilliam Ferreira Moreno Oliverio
William Ferreira Moreno Oliverio
ASAllan Barcelos Silva
Allan Barcelos Silva
SRSandro José Rigo
Sandro José Rigo
RCRodolpho Lopes Bezerra da Costa
Rodolpho Lopes Bezerra da Costa

12 July 2018 in Journal of Computer Science
Verified
Journal Article
Open access
PDF file
ASAllan de Barcelos Silva
Allan de Barcelos Silva
SRSandro José Rigo
Sandro José Rigo
Previous work on textual entailment has not fully exploited aspects of deep linguistic relations, which have been shown as containing important information for entailment identification. In this study, we present a new method to compute semantic textual similarity between two sentences. Our proposal relies on the integration of a set of deep linguistic relations, lexical aspects and distributed representational resources. We used our method with a large set of annotated data available from the ASSIN Workshop in the PROPOR 2016 event. The achieved results score among the best-known results in the literature. A perceived advantage of our approach is the ability to generate good results even with a small corpus on training tasks.

1 January 2019 in Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes
Verified
Journal Article
Open access
PDF file
ASAllan de Barcelos Silva
Allan de Barcelos Silva
ALAleksejs Lozkins
Aleksejs Lozkins
LBLuiz Ricardo Bertoldi
Luiz Ricardo Bertoldi
SRSandro José Rigo
Sandro José Rigo
VBVladimir Bure
Vladimir Bure

1 January 2018
Verified
Book Chapter
Closed access
ASAllan de Barcelos Silva
Allan de Barcelos Silva
SRSandro José Rigo
Sandro José Rigo
Jorge BarbosaJorge Barbosa
Jorge Barbosa
Research regarding stroke indicates that ensuring a short elapsed time between accident and treatment can be fundamental to allow saving patient's life and avoid future sequels. This paper describes a model for monitoring and rescuing victims in situations of possible stroke occurrence. It uses stroke symptoms that can be monitored by mobile equipment, ambient intelligence, and artificial neural networks. The model is independent of human operation and applications or third party devices, therefore adding facilities to increase the quality of life for people with stroke sequel, due to constant monitoring and follow-up provided, allowing the stroke patient to consider a recovery period with greater autonomy. A prototype based on free software platforms was developed, to assess the accuracy and the time elapsed between the prototype to detect and to send an alert. The results indicate a positive outcome for the work continuity.

1 October 2019 in Journal of Computer Science
Verified
Journal Article
Open access
PDF file
EBEduardo E. Berlitz
Eduardo E. Berlitz
DADenis A. Araujo
Denis A. Araujo
ASAllan B. Silva
Allan B. Silva
RRRodrigo R. Righi
Rodrigo R. Righi
SRSandro J. Rigo
Sandro J. Rigo
The similarity between words constitutes significant support to tasks in natural language processing. Several works use Lexical resources such as WordNet for semantic similarity and synonym identification. Nevertheless, words out-of-vocabulary or missing links between senses are perceived problems of this approach. Distributional-based proposals like word embeddings have successfully been used to meet such problems, but the lack of contextual information can prevent the achievement of even better results. The distributional models that include contextual information can bring advantages to this area, but these models are still scarcely explored. Therefore, this work studies the advantages of incorporating syntactic information in the distributional models, fostering for better results in semantic similarity approaches. For that purpose, the current work explore existing lexical and distributional techniques regarding the measurement of word similarity in Brazilian Portuguese. Experiments were carried out with the lexical database WordNet, using different techniques over a standard dataset. The results indicate that word embeddings can cover words out of vocabulary and have better results in comparison with lexical approaches. The main contribution of this article is a new approach to apply syntactic context in the training process of word embeddings to a Brazilian Portuguese corpus. The comparison of this model with the outcome of the previous experiments shows sound results and presents relevant complementary aspects.