Defesa de Proposta de Dissertação: Felipe Zschornack Rodrigues Saraiva


Título: Aspect Term Extraction Using Deep Learning Structures and Minimal Feature Engineering

Data: 01/11/2019

Horário: 16:30h

Local: Sala de Seminários - Bloco 952


This work proposes a neural network architecture using deep learning structures, and minimal feature engineering, to solve the problem of aspect term extraction in opinionated documents. Aspect term extraction (ATE) is the task of identifying aspects (attributes or characteristics) that have been evaluated in a sentence. The proposed architecture is similar to an Encoder-Decoder used in Neural Machine Translation, that uses an attention mechanism to permit the addition of grammatical relations between words as an additional feature. We also used the Part-of-speech tag (POS tags) as another relevant feature. The proposed architecture obtained state-of-the-art results, with the advantage of using no linguistic rules, only minimal feature engineering.


  • Prof. Dr. José Antonio Fernandes de Macêdo (MDCC/UFC - Orientador)
  • Profª. Drª. Ticiana Linhares Coelho da Silva (UFC)
  • Prof. Dr. João Paulo Pordeus Gomes(MDCC/UFC)

Última atualização (Qua, 30 de Outubro de 2019 14:16)