NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs

by   Christos Baziotis, et al.

In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 "Irony detection in English tweets". We design and ensemble two independent models, based on recurrent neural networks (Bi-LSTM), which operate at the word and character level, in order to capture both the semantic and syntactic information in tweets. Our models are augmented with a self-attention mechanism, in order to identify the most informative words. The embedding layer of our word-level model is initialized with word2vec word embeddings, pretrained on a collection of 550 million English tweets. We did not utilize any handcrafted features, lexicons or external datasets as prior information and our models are trained end-to-end using back propagation on constrained data. Furthermore, we provide visualizations of tweets with annotations for the salient tokens of the attention layer that can help to interpret the inner workings of the proposed models. We ranked 2nd out of 42 teams in Subtask A and 2nd out of 31 teams in Subtask B. However, post-task-completion enhancements of our models achieve state-of-the-art results ranking 1st for both subtasks.


page 1

page 2

page 3

page 4


NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention

In this paper we present a deep-learning model that competed at SemEval-...

NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning

In this paper we present deep-learning models that submitted to the SemE...

Clickbait Detection in Tweets Using Self-attentive Network

Clickbait detection in tweets remains an elusive challenge. In this pape...

DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs

This paper describes our approach for the Detecting Stance in Tweets tas...

Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder

We present Tweet2Vec, a novel method for generating general-purpose vect...

NL-FIIT at SemEval-2019 Task 9: Neural Model Ensemble for Suggestion Mining

In this paper, we present neural model architecture submitted to the Sem...

NTUA-SLP at IEST 2018: Ensemble of Neural Transfer Methods for Implicit Emotion Classification

In this paper we present our approach to tackle the Implicit Emotion Sha...

Please sign up or login with your details

Forgot password? Click here to reset