Year: 2018
Type: conference-paper
Abstract: In this paper we introduce our system for the task of Irony detection in English tweets, a part of SemEval 2018.We propose representation learning approach that relies on a multilayered bidirectional LSTM, without using external features that provide additional semantic information.Although our model is able to outperform the baseline in the validation set, our results show limited generalization power over the test set.Given the limited size of the dataset, we think the usage of more pretraining schemes would greatly improve the obtained results.
DOI: 10.18653/v1/s18-1087
Authors: Edison Marrese-Taylor, Suzana Ilic, Jorge Balazs, Helmut Prendinger, Yutaka Matsuo
Institutions: The University of Tokyo, National Institute of Informatics
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2798547941