Automatic Summarization of Noticias Crime in the Context of the Federal Police

• Thierry S. Barros Federal University of Campina Grande (UFCG)
• Carlos Eduardo S. Pires Federal University of Campina Grande (UFCG)
• Dimas C. N. Filho Federal University of Agreste do Pernambuco (UFAPE)

DOI: https://doi.org/10.5753/sbbd_estendido.2021.18174

Abstract

Deep neural networks have been successfully applied to many different Natural language processing tasks. A neural network model that leveraged the results in a wide range of NLP tasks was the BERT model - an acronym for Bidirectional Encoder Representations from Transformers. In this research, we present how the BERT model can be used for summarizing textual documents of the Brazilian Federal Police. The documents aim to report a summary of investigative activities. Due to the size and complexity of the documents, it is an exhausting job to read and understand their entire content. Thus, we aim to analyze the feasibility of using the BERT model to extract and synthesize the most important information from Federal Police documents.

Keywords: document summarization, federal police, bert

References

de Brito Gomes, L. B. and Oliveira, H. (2019). A multi-document summarization system for news articles in portuguese using integer linear programming.

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding.

Galassi, A., Lippi, M., and Torroni, P. (2019). Attention in natural language processing.

Jadhav, A., Jain, R., Fernandes, S., and Shaikh, S. (2019). Text summarization using neural networks. In 2019 International Conference on Advances in Computing, Communication and Control (ICAC3), pages 1–6.

Kiani, F. and Tas, O. (2017). A survey automatic text summarization. volume 5, pages 205–213.

Kieuvongngam, V., Tan, B., and Niu, Y. (2020). Automatic text summarization of covid19 medical research articles using bert and gpt-2.

Lin, C.-Y. (2004). Rouge: A package for automatic evaluation of summaries. page 10.

Liu, Y. (2019). Fine-tune bert for extractive summarization.

Moratanch, N. and Gopalan, C. (2017). A survey on extractive text summarization. pages 1–6.

Oliveira, M. A. d. and Mosca, L. d. L. S. (2014). As notícias de crime: uma análise retorico-argumentativa do discurso jornalístico online por antecipação ao discurso jurídico. Master’s thesis, Universidade de São Paulo.

Otter, D. W., Medina, J. R., and Kalita, J. K. (2019). A survey of the usages of deep learning in natural language processing.

Rino, L., Pardo, T., Silla, C., Kaestner, C., and Pombo, M. (2004). A comparison of automatic summarizers of texts in brazilian portuguese. volume 3171, pages 235–244.

Widyassari, A. P., Rustad, S., Shidik, G. F., Noersasongko, E., Syukur, A., Affandy, A., and Setiadi, D. R. I. M. (2020). Review of automatic text summarization techniques methods. Journal of King Saud University - Computer and Information Sciences.