English

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

Computation and Language 2018-04-19 v1

Abstract

In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 "Multilingual Emoji Prediction". We participated in subtask A, in which we are called to predict the most likely associated emoji in English tweets. The proposed architecture relies on a Long Short-Term Memory network, augmented with an attention mechanism, that conditions the weight of each word, on a "context vector" which is taken as the aggregation of a tweet's meaning. Moreover, we initialize the embedding layer of our model, with word2vec word embeddings, pretrained on a dataset of 550 million English tweets. Finally, our model does not rely on hand-crafted features or lexicons and is trained end-to-end with back-propagation. We ranked 2nd out of 48 teams.

Keywords

Cite

@article{arxiv.1804.06657,
  title  = {NTUA-SLP at SemEval-2018 Task 2: Predicting Emojis using RNNs with Context-aware Attention},
  author = {Christos Baziotis and Nikos Athanasiou and Georgios Paraskevopoulos and Nikolaos Ellinas and Athanasia Kolovou and Alexandros Potamianos},
  journal= {arXiv preprint arXiv:1804.06657},
  year   = {2018}
}

Comments

SemEval-2018, Task 2 "Multilingual Emoji Prediction"

R2 v1 2026-06-23T01:27:27.151Z